阅读说明：本技术 用于区分组织状态和类型的系统、方法和计算机产品 (System, method and computer product for differentiating between tissue states and types ) 是由 S·托莱达诺 M·图瓦 S·盖特 于 2019-06-12 设计创作，主要内容包括：本发明公开了一种用于区分组织状态或类型的方法,包括：接收组织的热数据的序列,其中当组织被热扰动时,在组织的至少一个位置处对序列进行采样；从热数据导出与组织位置中的每个位置相关联的至少一个组织相关热变量；将组织分割成区段,该区段包括具有对应的至少一个热变量的位置；以及生成指示组织区段的输出。本公开还包括用于区分组织状态或类型的系统和计算机产品。(The invention discloses a method for distinguishing tissue states or types, which comprises the following steps: receiving a sequence of thermal data of tissue, wherein the sequence is sampled at least one location of the tissue when the tissue is thermally perturbed; deriving from the thermal data at least one tissue-related thermal variable associated with each of the tissue locations; segmenting tissue into segments comprising locations having corresponding at least one thermal variable; and generating an output indicative of the tissue section. The present disclosure also includes systems and computer products for differentiating between states or types of tissue.)

1. A method, comprising:

receiving a sequence of thermal data of a tissue, wherein the sequence is sampled at least one location of the tissue when the tissue is thermally perturbed;

deriving from the thermal data at least one thermal variable associated with each of the tissue locations;

segmenting the tissue into segments comprising the locations with the corresponding at least one thermal variable; and

generating an output indicative of the tissue segment.

2. The method of claim 1, wherein the thermal data is received from at least one of: thermal imaging, infrared sensors, i.e., IR sensors, mercury thermometers, resistance thermometers, thermistors, thermocouples, semiconductor-based temperature sensors, pyrometers, gas thermometers, laser thermometers, and ultrasound.

3. The method of claim 2, wherein the thermal data is received by thermal imaging, and wherein the locations comprise pixels or voxels of an image.

4. The method of any one of the preceding claims, wherein the at least one thermal variable is selected from the group consisting of: a tissue organism metabolic heat source, heat loss due to blood perfusion, blood temperature, tissue density, specific heat, tissue thermal conductivity factor, tissue thermal conductivity coefficient, tissue thermal conductivity surface area, tissue surface temperature, and time-dependent thermal gradient between tissue and ambient temperature.

5. The method of any one of the preceding claims, wherein the at least one thermal variable further comprises at least one of an ambient temperature and a heat source temperature.

6. The method of any preceding claim, wherein the thermal perturbation comprises at least one of: actively effecting a temperature change in at least a portion of the tissue from an initial temperature to a final temperature, actively effecting a temperature change in at least a portion of the tissue for a specified period of time, passively allowing a temperature change in at least a portion of the tissue from an initial temperature to a final temperature, and passively allowing a temperature change in at least a portion of the tissue for a specified period of time.

7. The method of any preceding claim, comprising extracting a set of features based on at least some of the thermal data and thermal variables, wherein the features are selected from a group of features comprising: features representing various derivative values of the variable, features representing noise in the variable, attenuation equation-based features, fourier series-based features, and correlation features based on differences in the features.

8. The method of claim 7, wherein the segmenting is further based on the locations having a corresponding set of features.

9. The method of any of the preceding claims, wherein the correspondence is determined based at least in part on all of the variables and the difference values of the features not exceeding a specified threshold.

10. The method of any of the preceding claims, further comprising determining a tissue state or type associated with each of the segments based at least in part on correlating the at least one thermal variable to a predetermined value of the thermal variable associated with a plurality of tissue states or types.

11. The method of any of the preceding claims, wherein the correlating further comprises correlating the features.

12. The method of any preceding claim, wherein the deriving, segmenting, extracting and determining are performed by a machine learning classifier that is trained in a training phase against a training set comprising:

(i) a plurality of thermal data sequences, each thermal data sequence being sampled at least one location of tissue when the tissue is thermally perturbed; and

(ii) a tag associated with a status or type of the at least one location.

13. The method of claim 12, further comprising applying the trained machine learning classifier to at least one target thermal data sequence sampled at a location of tissue when the tissue is thermally perturbed in an inference stage to determine a state or type of the tissue location.

14. A computer program product comprising a non-transitory computer-readable storage medium having program code embodied therewith, the program code executable by at least one hardware processor to:

receiving a sequence of thermal data of a tissue, wherein the sequence is sampled at least one location of the tissue when the tissue is thermally perturbed;

deriving from the thermal data at least one tissue-related thermal variable associated with each of the tissue locations;

segmenting the tissue into segments comprising the locations with the corresponding at least one thermal variable; and

generating an output indicative of the tissue segment.

15. The computer program product of claim 14, wherein the at least one thermal variable is indicative of a state or type of the tissue.

16. The computer program product of any one of claims 14 and 15, wherein the thermal data is received from at least one of: thermal imaging, infrared sensors, i.e., IR sensors, mercury thermometers, resistance thermometers, thermistors, thermocouples, semiconductor-based temperature sensors, pyrometers, gas thermometers, laser thermometers, and ultrasound.

17. The computer program product of any of claims 14 to 16, wherein the thermal data is received by thermal imaging, and wherein the location comprises a pixel or a voxel.

18. The computer program product of any one of claims 14 to 17, wherein the thermally perturbed tissue comprises actively or passively effecting a temperature change from an initial temperature to a final temperature over at least a portion of the tissue.

19. The computer program product of any one of claims 14 to 18, wherein the thermally perturbed tissue comprises effecting a temperature change on at least a portion of the tissue for at least one predetermined period of time.

20. The computer program product according to any one of claims 14 to 19, wherein the at least one tissue-related thermal variable comprises at least one intrinsic tissue thermal parameter that affects thermal behavior of cells.

21. The computer program product of any of claims 14 to 20, comprising calculating a set of features based on at least some of the thermal data and thermal variables.

22. The computer program product of claim 21, wherein the features are selected from a group of features comprising: features representing various derivative values of the variable, features representing noise in the variable, attenuation equation-based features, fourier series-based features, and correlation features based on differences in the features.

23. The computer program product of any of claims 21 to 22, wherein the segmenting is further based on the location having a corresponding set of features.

24. The computer program product of claim 23, wherein the correspondence is determined based at least in part on all of the variables and the difference values of the features not exceeding a specified threshold.

25. The computer program product of any one of claims 14 to 24, wherein the deriving comprises calculating a set of thermal signatures for each of the tissue locations based at least in part on the at least one thermal variable.

26. A system, comprising:

a thermal sensor configured to sample a sequence of thermal data from at least one location on tissue as the tissue is thermally perturbed; and

a processor configured to:

deriving from the thermal data at least one tissue-related thermal variable associated with each of the tissue locations;

segmenting the tissue into segments comprising the locations with the corresponding at least one thermal variable; and

generating an output indicative of the tissue segment.

27. The system of claim 26, wherein the system comprises a heating or cooling source directed at least at the tissue surface and configured to actively heat or cool the tissue.

28. The system of any one of claims 26 to 27, wherein the at least one thermal variable is indicative of a state or type of the tissue.

29. The system of any one of claims 26 to 28, wherein the thermal data is received from at least one of: thermal imaging, infrared sensors, i.e., IR sensors, mercury thermometers, resistance thermometers, thermistors, thermocouples, semiconductor-based temperature sensors, pyrometers, gas thermometers, laser thermometers, and ultrasound.

30. The system of any one of claims 26 to 29, wherein the thermal data is received by thermal imaging, and wherein the locations comprise pixels or voxels.

31. The system of any one of claims 26 to 30, wherein the thermally perturbed tissue comprises actively or passively effecting a temperature change from an initial temperature to a final temperature over at least a portion of the tissue.

32. The system of any one of claims 26 to 31, wherein the thermally perturbed tissue comprises effecting a temperature change on at least a portion of the tissue for at least one predetermined period of time.

33. The system of any one of claims 26 to 32, wherein the at least one tissue-related thermal variable comprises at least one intrinsic tissue thermal parameter that affects thermal behavior of cells.

34. The system of any one of claims 26 to 33, comprising calculating a set of features based on at least some of the thermal data and thermal variables.

35. The system of any one of claims 34, wherein the features are selected from a group of features comprising: features representing various derivative values of the variable, features representing noise in the variable, attenuation equation-based features, fourier series-based features, and correlation features based on differences in the features.

36. The system of any of claims 34 to 35, wherein the segmenting is further based on the location having a corresponding set of features.

Technical Field

In some embodiments thereof, the present invention relates to thermal data collection systems, methods, and computer products.

Background

Thermography is a field in which thermal radiation, such as infrared radiation emitted from an object, is detected by a sensor (e.g. a thermographic camera), which converts the sensed thermal radiation into an image (thermogram). A thermogram allows observation of differences in thermal radiation emitted from various regions above the surface of an imaged object.

Without external thermal intervention (passive thermography), the thermal radiation emitted from the object may be higher or lower than the background thermal radiation emitted. Passive thermography has many applications such as personnel monitoring and medical diagnostics (particularly thermal) against background.

Unlike passive thermography, the energy source may actively heat the object (active thermography) to create a thermal contrast between the object and the background. Active thermography is used in situations where the object under examination is in equilibrium with the surrounding environment.

The foregoing examples of the related art and limitations related thereto are intended to be illustrative and not exclusive. Other limitations of the related art will become apparent to those of skill in the art upon a reading of the specification and a study of the drawings.

Disclosure of Invention

The following embodiments and aspects thereof are described and illustrated in conjunction with systems, tools, and methods which are meant to be exemplary and illustrative, not limiting in scope.

According to an aspect according to some embodiments of the present invention there is provided a method for distinguishing between tissue states or types, comprising: receiving a sequence of thermal data of tissue, wherein the sequence is sampled at least one location of the tissue when the tissue is thermally perturbed; deriving from the thermal data at least one thermal variable associated with each of the tissue locations; segmenting tissue into segments comprising locations having corresponding at least one thermal variable; and generating an output indicative of the tissue section.

According to some embodiments, the thermal data is received from at least one of: thermal imaging, Infrared (IR) sensors, mercury thermometers, resistance thermometers, thermistors, thermocouples, semiconductor-based temperature sensors, pyrometers, gas thermometers, laser thermometers, and ultrasound. In some embodiments, the thermal data is received by thermal imaging, and wherein the locations comprise pixels or voxels of the image. In some embodiments, the at least one thermal variable is selected from the group consisting of: a tissue organism metabolic heat source, heat loss due to blood perfusion, blood temperature, tissue density, specific heat, tissue thermal conductivity factor, tissue thermal conductivity coefficient, tissue thermal conductivity surface area, tissue surface temperature, and time-dependent thermal gradient between tissue and ambient temperature.

In some embodiments, the at least one thermal variable further comprises at least one of an ambient temperature and a heat source temperature. In some embodiments, the thermal perturbation comprises at least one of: actively effecting a temperature change in at least a portion of the tissue from an initial temperature to a final temperature, actively effecting a temperature change in at least a portion of the tissue for a specified period of time, passively allowing a temperature change in at least a portion of the tissue from an initial temperature to a final temperature, and passively allowing a temperature change in at least a portion of the tissue for a specified period of time.

According to some embodiments, the method comprises extracting a set of features based on at least some of the thermal data and the thermal variables, wherein the features are selected from a group of features comprising: features representing various derivative values of the variable, features representing noise in the variable, attenuation equation-based features, fourier series-based features, and correlation features based on differences in the features. In some embodiments, the segmentation is further based on the location having a corresponding set of features. In some embodiments, the correspondence is determined based at least in part on the disparity values of all variables and features not exceeding a specified threshold. In some embodiments, the method further comprises determining a tissue state or type associated with each of the segments based at least in part on correlating the at least one thermal variable to a predetermined value of the thermal variable associated with the plurality of tissue states or types. In some embodiments, correlating further comprises correlating the features.

In some embodiments, the deriving, segmenting, extracting, and determining are performed by a machine learning classifier, the machine learning classifier being trained, in a training phase, against a training set, the training set comprising a plurality of thermal data sequences, each thermal data sequence being sampled at least one location of the tissue when the tissue is thermally perturbed; and a tag associated with a status or type of at least one location.

In some embodiments, the method further comprises applying, in an inference phase, the trained machine learning classifier to at least one target thermal data sequence sampled at the location of the tissue when the tissue is thermally perturbed to determine the state or type of the tissue location.

According to an aspect according to some embodiments of the present invention, there is provided a computer program product comprising a non-transitory computer-readable storage medium having program code embodied therewith, the program code executable by at least one hardware processor to: receiving a sequence of thermal data of tissue, wherein the sequence is sampled at least one location of the tissue when the tissue is thermally perturbed; deriving from the thermal data at least one tissue-related thermal variable associated with each of the tissue locations; segmenting tissue into segments comprising locations having corresponding at least one thermal variable; and generating an output indicative of the tissue section. In some embodiments, the at least one thermal variable is indicative of a state or type of tissue.

In some embodiments, the thermal data is received from at least one of: thermal imaging, Infrared (IR) sensors, mercury thermometers, resistance thermometers, thermistors, thermocouples, semiconductor-based temperature sensors, pyrometers, gas thermometers, laser thermometers, and ultrasound. In some embodiments, the thermal data is received by thermal imaging, and wherein the locations comprise pixels or voxels. In some embodiments, thermally perturbing the tissue includes actively or passively effecting a temperature change from an initial temperature to a final temperature over at least a portion of the tissue.

In some embodiments, thermally perturbing the tissue includes effecting a temperature change over at least a portion of the tissue for at least one predetermined period of time. In some embodiments, the at least one tissue-related thermal variable comprises at least one intrinsic tissue thermal parameter that affects the thermal behavior of the cells. In some embodiments, the computer program product is configured to calculate the set of features based on at least some of the thermal data and the thermal variables.

In some embodiments, the features are selected from a group of features comprising: features representing various derivative values of the variable, features representing noise in the variable, attenuation equation-based features, fourier series-based features, and correlation features based on differences in the features. In some embodiments, the segmentation is further based on the location having a corresponding set of features.

In some embodiments, the correspondence is determined based at least in part on the disparity values of all variables and features not exceeding a specified threshold. In some embodiments, deriving comprises calculating a set of thermal signatures for each of the tissue locations based at least in part on the at least one thermal variable.

According to an aspect according to some embodiments of the invention, there is provided a system comprising: a thermal sensor configured to sample a sequence of thermal data from at least one location on the tissue when the tissue is thermally perturbed; and a processor configured to: deriving from the thermal data at least one tissue-related thermal variable associated with each of the tissue locations; segmenting tissue into segments comprising locations having corresponding at least one thermal variable; and generating an output indicative of the tissue section, wherein the system comprises a heating or cooling source directed at least at the tissue surface and configured to actively heat or cool the tissue.

In some embodiments, the at least one thermal variable is indicative of a state or type of tissue. In some embodiments, the thermal data is received from at least one of: thermal imaging, Infrared (IR) sensors, mercury thermometers, resistance thermometers, thermistors, thermocouples, semiconductor-based temperature sensors, pyrometers, gas thermometers, laser thermometers, and ultrasound. In some embodiments, the thermal data is received by thermal imaging, and wherein the locations comprise pixels or voxels.

In some embodiments, thermally perturbing the tissue includes actively or passively effecting a temperature change from an initial temperature to a final temperature over at least a portion of the tissue. In some embodiments, thermally perturbing the tissue includes effecting a temperature change over at least a portion of the tissue for at least one predetermined period of time. In some embodiments, the at least one tissue-related thermal variable comprises at least one intrinsic tissue thermal parameter that affects the thermal behavior of the cells.

In some embodiments, thermal data and thermal variables. In some embodiments, the features are selected from a group of features comprising: features representing various derivative values of the variable, features representing noise in the variable, attenuation equation-based features, fourier series-based features, and correlation features based on differences in the features. In some embodiments, the segmentation is further based on the location having a corresponding set of features.

In addition to the exemplary aspects and embodiments described above, further aspects and embodiments will become apparent by reference to the drawings and by study of the following detailed description.

Drawings

Exemplary embodiments are shown in the drawings. The dimensions of the features and characteristics shown in the figures are generally chosen for convenience and clarity of presentation and are not necessarily shown to scale. The figures are listed below.

FIG. 1 is a simplified diagram of a thermal imaging system for differentiating and/or identifying tissue states or types according to some embodiments of the present invention;

FIGS. 2A and 2B are graphs of thermal curves associated with the biological thermal behavior of tissue cells under temperature changes, according to some embodiments of the invention;

FIG. 3 is a graph of thermal curves associated with the biological thermal behavior of tissue cells under temperature changes according to some embodiments of the invention;

FIG. 4 is a graph of thermal curves associated with the biological thermal behavior of tissue cells under temperature changes according to some embodiments of the invention;

5A, 5B, and 5C are graphs indicating peak temperature points according to some embodiments of the invention;

6A, 6B, 6C, and 6D are exemplary screen images of a thermal imaging system display according to some embodiments of the invention;

FIG. 7 is an exemplary simplified flowchart illustrating the operation of a thermal imaging system processor according to some embodiments of the invention;

FIGS. 8A and 8B are simplified graphs illustrating a difference data set of cross-sectional points according to some embodiments of the present invention;

FIG. 9A is a simplified illustration of a plan view of a thermal profile over a portion of a tissue surface, according to some embodiments of the invention;

fig. 9B is a thermal profile of cells within a portion of a tissue surface according to some embodiments of the invention;

10A, 10B, and 10C are simplified illustrations in plan view of a thermal distribution over a portion of a tissue surface, according to some embodiments of the invention;

11A and 11B are simplified illustrations in plan view of a thermal distribution over a portion of a tissue surface, according to some embodiments of the invention;

FIG. 12 is a graph and plan view simplified illustration of a thermal profile over a portion of a tissue surface, according to some embodiments of the invention;

FIG. 13 is an exemplary simplified flowchart illustrating the operation of a thermal imaging system processor according to some embodiments of the invention;

14A and 14B are graphs of thermal curves associated with the biological thermal behavior of heated cells, according to some embodiments of the invention;

FIG. 15 is a graph of a thermal profile associated with the biological thermal behavior of heated cells according to some embodiments of the invention; and

fig. 16A and 16B are simplified illustrations of cross-sectional views of thermal distributions within portions of a tissue surface according to some embodiments of the present invention.

Detailed Description

According to an aspect of some embodiments of the present invention there is provided a method for distinguishing one or more tissue locations or regions based at least in part on thermal properties associated with the locations or regions calculated from thermal data. In some embodiments, thermal data is collected from at least one location on the tissue. In some embodiments, the method includes collecting a time series of thermal data for at least one location while affecting thermal changes in the tissue.

As used herein, the term "tissue" includes any body or body-related material, such as soft tissue, hard tissue, and cellular and non-cellular material, e.g., muscle, bone, teeth, and/or bacteria.

In some embodiments, the present disclosure provides for differentiating between states and/or types of tissue. In some embodiments, the tissue type includes, but is not limited to, muscle, bone, neural tissue, blood vessels, glandular tissue, and/or adipose tissue.

In some embodiments, the tissue condition includes, but is not limited to, a tissue clinical condition, such as normal tissue, inflamed tissue, tissue tumor, tissue dysplasia, mucosal cyst, fibroids, fibroepithelial polyps, pathological tissue, pre-cancerous tissue, and/or cancerous tissue.

Although tissue thermal data may be sampled by a number of sensing devices, such as Infrared (IR) sensors, mercury thermometers, resistance thermometers, thermistors, thermocouples, semiconductor-based temperature sensors, pyrometers, gas thermometers, laser thermometers, and ultrasound, for purposes of clarity and simplicity, the determination of the status of one or more tissue locations is demonstrated hereinafter, by way of example and not limitation, based on thermal properties calculated from data received by thermal imaging.

According to an aspect according to some embodiments of the present invention, there is provided a method for differentiating tissue according to tissue state or type, the method being based at least in part on a temperature change affecting at least one surface of at least a portion of the tissue. For example, in some embodiments, effecting a temperature change includes at a predetermined first time period (e.g., t)₀To t₁) At least one surface of at least a portion of the tissue is heated from an initial base temperature and then the temperature of the tissue is allowed to stand for a second period of time (e.g., t)₁To t₂) Passively returned (e.g., cooled) to the base temperature.

In some embodiments, the first time period and the second time period t are combined₀To t₂During this time, a sequence of thermal data (e.g., thermal images (e.g., a video stream)) of at least the tissue surface is obtained using one or more suitable thermal imaging devices (e.g., Infrared (IR), Near Infrared (NIR), Short Wave Infrared (SWIR), and/or another imaging device). In some embodiments, the time period t may be₁To t₂Additional images and/or image streams are obtained during at least a portion of (a). In some embodiments, the additional images may include red, green, blue (RGB) images, monochromatic images, Ultraviolet (UV) images, multispectral images, and/or hyperspectral images.

In some embodiments, the image data is processed to extract a plurality of values associated with at least some of the pixels in each image. In some embodiments, some portion of the value may be extracted at a point in time and/or over part or all of time period t₀To t₂The intra-extraction is as a time series.

In some embodiments, the one or more values may be converted into one or more feature vectors, including a plurality of time-dependent feature vectors. In some embodiments, one or more feature vectors may be compared to predetermined features or feature vectors associated with one or more tissue states or types. In some embodiments, the state of one or more regions of tissue may be determined based at least in part on the comparison.

In some embodiments, the one or more feature vectors for each pixel are grouped into one or more groups indicating regions where the group is a tissue state or type of tissue being imaged.

In some embodiments, the present disclosure provides an output indicative of a tissue state or type of one or more regions of thermally imaged tissue. In some embodiments, the output may include an image including a graphical representation of one or more regions based at least in part on the identified tissue state or type associated with each region. For example, in some embodiments, each region may be bounded and/or some or all of the regions may be presented using one or more color schemes. In some embodiments, the graphical representation may be generated as a thermal image, an RGB image, and/or another and/or different type of image. In some embodiments, the boundaries of the identified tissue state or type are drawn (mapped) on a tissue state profile. In some embodiments, the boundaries of the identified tissue state or type are plotted in the form of a graph, such as a histogram.

In some embodiments, a machine learning classifier may be trained on a data set comprising a set of feature vectors associated with a plurality of subject tissues, wherein the training data set may be labeled with one or more tissue states or types present in several regions of the subject tissue. In some embodiments, the trained classifier of the present disclosure may then be applied to a target feature set from a target subject to determine the presence of one or more physiological or pathological parameters in a target tissue.

In some embodiments, actively changing the temperature of the tissue includes actively heating or actively or passively cooling portions of the tissue during at least a portion of the imaging period.

In some embodiments, the processing or analysis is performed on each pixel of the obtained image. In some embodiments, the analyzing includes extracting a plurality of pixel level values for each pixel, which represent a quantification of a physiological or pathological parameter.

In some embodiments, the method includes receiving a sequence of thermal data of tissue, wherein the sequence is sampled at one or more locations of the tissue when the tissue is thermally perturbed; deriving from the thermal data at least one tissue-related thermal variable associated with each of the tissue locations; segmenting tissue into segments comprising locations having corresponding one or more thermal variables; and generating an output indicative of the tissue section.

In some embodiments, the method includes calculating a set of features based on at least some of the thermal data and the thermal variables, in which case the segmentation has a corresponding set of features based on the location. In some embodiments, the correspondence is determined based at least in part on the disparity values of all variables and features not exceeding a specified threshold. In some embodiments, the method includes calculating a set of thermal signatures for each of the tissue locations based at least in part on the one or more thermal variables. In some embodiments, the one or more thermal variables are indicative of a state or type of tissue. In some embodiments, the features are selected from a group of features comprising: features representing various derivative values of the variable, features representing noise in the variable, attenuation equation-based features, fourier series-based features, and correlation features based on differences in the features.

In some embodiments, the method includes acquiring a sequence of thermal images over a period of time. In some embodiments, for each pixel and/or measurement point, pixel values are extracted from the thermal image, a feature vector is generated that represents the thermal properties of tissue cells over a time period, pixels with similar features are clustered into clusters, and the clusters of pixels are reflected onto corresponding regions in the imaged tissue. In some embodiments, the method includes determining the tissue status or type of the at least one region based on comparing the features to a set of known features of the tissue status or type. In some embodiments, the method includes generating an output, e.g., a graphical representation of the state of the tissue in one or more regions. In some embodiments, the method includes classifying the tissue state in each region using a trained machine learning classifier. In some embodiments, generating the feature vector is optional, and the method includes determining the tissue state or type of the at least one region based on comparing the feature to a set of known features of the tissue state or type.

In some embodiments, the method includes generating a map representing a distribution of thermal variables and/or thermal characteristics over a portion of tissue within an imaging field of view (FOV). In some embodiments, the method includes analyzing a distribution over a graph of pixel value values, and identifying clusters of values, each cluster being within the same pixel value range, and associating the identified values with a particular tissue type or state. In some embodiments, clusters of pixels in thermal images that share the same value are associated with corresponding clusters of a particular tissue cell type.

In some embodiments, the distribution analysis of pixel level values is based on the calculation of differences between calculated pixel level values.

In some embodiments, the method includes generating a plurality of pixel level value profiles, each pixel level value profile associated with a particular physiological or pathological parameter. In some embodiments, multiple maps generated from the obtained pixel level values are combined or superimposed to enhance identification of clusters of tissue cell types.

According to an aspect according to some embodiments of the present invention, there is provided a method for distinguishing a state or type of tissue. In some embodiments, the method includes obtaining a pixel level value from a thermal image of at least a portion of tissue within a field of view (FOV) of a thermal imager. In some embodiments, the method includes actively changing the temperature of a portion of tissue over a set period of time. In some embodiments, the method includes obtaining thermal images (frames) of the tissue during the temperature change. In some embodiments, the method includes processing successive frames of obtained pixel level values, and extracting pixel level values relating to changes in one or more variables or features over a set period of time, the variables or features being derived from pixel level values representing physiological or pathological parameters associated with tissue.

In some embodiments, the method includes generating a graph for each pixel that represents a change in pixel level value, thermal variable, or characteristic derived from the pixel level value during a change in tissue temperature. In some embodiments, the method includes processing, for example, by performing a comparative analysis on one or more portions of the curve of the graph and identifying groups of pixels having similar or identical curve patterns associated with a particular tissue state or type. In some embodiments, the identified groups of pixels that share the same pixel level value, variable, or characteristic are associated with a particular type or state of tissue. In some embodiments, the distribution analysis of pixel level values, variables or features is based on the calculation of differences between graph curves, the graph curves based on values obtained from each pixel.

In some embodiments, the method includes actively heating the tissue and allowing the tissue to cool passively. In some embodiments, the processing of the imaging frames obtained during the periods of active heating and passive cooling is represented by a graph curve having a growing portion, a peak portion, and a decaying portion. In some embodiments, a thermal imaging system includes a processor and a computer program product configured to perform a comparative analysis on only a growing portion of a resulting curve. In some embodiments, the comparative analysis is performed only on the attenuated portion of the resulting curve. In some embodiments, the computer program product of the processor is configured to perform a comparative analysis on the peak temperature of the curve only at the intersection of the increasing portion and the decreasing portion of the resulting curve.

Alternatively and optionally, in some embodiments and as shown, for example, in fig. 2B, the method includes actively cooling the tissue and allowing the tissue to passively warm up. In some embodiments, analysis of imaging frames obtained during periods of active cooling and passive warming is expressed by a graphical curve having a decay portion, a valley (minimum point), and a growth portion. In some embodiments, a thermal imaging system includes a processor and a computer program product configured to perform a comparative analysis on only a growing portion of a resulting curve. In some embodiments, the comparative analysis is performed only on the attenuated portion of the resulting curve. In some embodiments, the computer program product of the processor is configured to perform a comparative analysis on the curve valley (lowest temperature) only at the intersection of the increasing and decreasing portions of the resulting curve.

In some embodiments, the method includes processing by performing a comparative analysis of differences in seasonal noise from the curve for each pixel and identifying clusters of pixels having similar curve seasonal noise associated with the tissue state or type. In some embodiments, the identified clusters are associated with tissue cell clusters.

In some embodiments, the method includes generating a plurality of distribution maps, each distribution map based on a generated pixel level value associated with a particular physiological parameter. In some embodiments, multiple generated maps are combined or superimposed to enhance the identification of the state or type of tissue cell clusters.

In some embodiments, the method includes gradually actively heating or cooling the portion of tissue. In some embodiments, the method includes obtaining thermal images (frames) over a set period of time. In some embodiments, the method includes processing successive frames of images obtained during each active heating or cooling increment, and extracting pixel level values for changes in one or more physiological or pathological parameters associated with the tissue within the heating increment.

According to an aspect according to some embodiments of the present invention, there is provided a method for distinguishing a state or type of tissue. In some embodiments, the method includes actively heating the tissue. In some embodiments, heating the tissue includes applying a linear beam of heating energy (e.g., infrared light) to one side of the tissue, thereby heating the strip of tissue. In some embodiments, the method includes obtaining thermal images (frames) of portions of tissue within the FOV of the thermal imager over a set period of time.

Alternatively and optionally, in some embodiments, the method for distinguishing the state or type of tissue comprises actively cooling the tissue. In some embodiments, cooling the tissue includes applying a linear beam of cooling energy (e.g., a spray or contact coolant) to one side of the tissue, thereby cooling the tissue strip. In some embodiments, the method includes obtaining thermal images (frames) of portions of tissue within the FOV of the thermal imager over a set period of time.

In some embodiments, the method includes processing successive frames of images obtained over a time period, and extracting pixel level values relating to a rate of thermal diffusion in a direction perpendicular to the vector beam and/or the heated tissue strip during the set time period. In some embodiments, processing successive frames of images obtained over a particular time period includes associating pixel-level values relating to a rate of thermal diffusion in tissue with one or more physiological or pathological parameters associated with the tissue. In some embodiments, the method includes identifying clusters of pixels that share a pixel level value or variable or characteristic based on pixel level values associated with diffusion rates within a given range of diffusion rates associated with a tissue type or state. In some embodiments, the identified clusters of pixels are associated with corresponding clusters of cells of a particular tissue type or state on the graphical representation of the imaged tissue.

According to an aspect according to some embodiments of the present invention, there is provided a method for distinguishing a state or type of tissue. In some embodiments, the method includes heating tissue. In some embodiments, heating the tissue includes applying heating energy (e.g., infrared light) to any portion of the tissue surface. Alternatively and optionally, in some embodiments, the method comprises actively cooling the tissue. In some embodiments, cooling the tissue includes applying cooling energy (e.g., a spray or contact coolant) to any portion of the tissue surface. In some embodiments, the method includes obtaining thermal images of a portion of tissue within the FOV of the thermal imager over a set period of time.

In some embodiments, the method includes processing successive frames of thermal images (frames) acquired over a period of time, and extracting pixel level values relating to a rate of thermal diffusion on a tissue surface during the set period of time. In some embodiments, processing successive frames of images obtained over a particular time period includes correlating information about the rate of heat diffusion in tissue with one or more physiological or pathological parameters associated with the tissue. In some embodiments, the method includes identifying clusters of pixels that share a diffusion rate within a given range associated with a tissue type. In some embodiments, the identified clusters are associated with corresponding clusters of cells of a particular tissue type on the graphical representation of the imaged tissue.

According to an aspect according to some embodiments of the present invention, there is provided a method for distinguishing a state or type of tissue. In some embodiments, the method includes heating tissue. In some embodiments, heating the tissue includes applying heating energy (e.g., infrared light) to a predetermined depth within the tissue. In some embodiments, the method includes obtaining thermal images of portions of tissue at various depths between the tissue surface and the predetermined depth over a set period of time.

Alternatively and optionally, in some embodiments, the method for distinguishing the state or type of tissue comprises actively cooling the tissue. In some embodiments, cooling the tissue includes applying cooling energy (e.g., a spray or contact coolant) to a predetermined depth within the tissue. In some embodiments, the method includes obtaining thermal images (frames) of portions of tissue at various depths between the tissue surface and the predetermined depth over a set period of time.

In some embodiments, the method includes processing successive frames of thermal images obtained at any particular depth over a period of time, and extracting pixel level values relating to the rate of heat diffusion throughout the tissue layer at the particular depth during the set period of time. In some embodiments, processing successive frames of images obtained over a particular time period includes associating a pixel level value associated with a rate of thermal diffusion within tissue with one or more physiological or pathological parameters associated with the tissue. In some embodiments, the method includes identifying clusters of voxels that share a diffusion rate within a given range associated with a particular tissue type or state. In some embodiments, the identified clusters of pixels are associated with corresponding clusters of cells of a particular tissue type or state on the graphical representation of the imaged tissue.

According to an aspect according to some embodiments of the present invention, there is provided a computer program product, comprising a non-transitory computer-readable storage medium having program code embodied therewith, the program code executable by at least one hardware processor to process one or more thermal images (frames) of a portion of tissue within a field of view (FOV) of a thermal imager.

In some embodiments, the computer program product is executable to calculate from information received from each pixel of the obtained image. In some embodiments, the program product is executable to calculate a pixel level value associated with a physiological or pathological parameter of the tissue. In some embodiments, the program product is executable to generate a map based on calculated values associated with physiological or pathological parameters of the tissue. In some embodiments, the program product is executable to indicate a cluster of pixels having values associated with parameters within a given parameter range associated with a particular tissue type or state.

In some embodiments, the computer program product is executable to calculate a series of variables and/or features based on pixel level values received from at least one pixel over a set period of time and associated with changes in physiological or pathological parameters of the tissue. In some embodiments, the program product is executable to calculate variables and/or features from a plurality of image frames taken over a set period of time. In some embodiments, the program product is executable to generate a curve based on calculated variables and/or features associated with changes in physiological or pathological parameters of the tissue over a set period of time. In some embodiments, the program product may be executable to indicate clusters of pixels having similar curves and associated with differences in parameters within a given range or above a given threshold associated with a particular tissue type or state.

System for controlling a power supply

Reference is now made to fig. 1. The figure is a simplified diagram of a thermal imaging system for differentiating and/or identifying tissue states or types according to some embodiments of the present invention. In some embodiments, the thermal imaging system 100 for distinguishing and/or identifying a tissue state or type includes a thermal imager 108, which thermal imager 108 images the surface of the tissue 104 as it is actively heated or cooled. In some embodiments, the thermal imager 108 is in communication with a processor 110. The processor 110 of the thermal imaging system 100 is configured to process thermal images obtained by the thermal imager 108 and generate an output map, for example, on the display 112.

In some embodiments, the output map includes a graphical representation of the calculated pixel level values. In some embodiments, the output map includes a graphical representation of the calculated pixel level values superimposed on the RGB image or any other graphical representation of the imaged tissue. In some embodiments, the output map comprises a graphical representation of the calculated differences in the calculated pixel level values relative to the golden standard value. In some embodiments, the output map includes a graphical representation of the calculated differences in pixel level values superimposed on the RGB image or any other graphical representation of the imaged tissue.

As shown in FIG. 1, a thermal imaging system 100 for differentiating and/or identifying a tissue state or type includes a heating/cooling source 102 directed at a surface of tissue 104 to be treated. The surface of tissue 104 may be the surface of any tissue or organ in the body, for example, skin, liver, spleen, kidney, and bladder. In the embodiment shown in fig. 1, the surface of the tissue 104 includes a population of cells of the abnormal tissue 106.

In some embodiments, active heating may include one or more heating methods selected from a range of heating methods including radiation, convection, and conduction. The heat source 102 may be, for example, any suitable heat source, such as an LEDHigh radiant flux density 400nm violet LED emitters LZP-D0UB00-00U5 manufactured by San Jose CA 95134, USA or any Infrared (IR), Radio Frequency (RF), Ultrasound (US), fluid flow over tissue surfaces, heating tubes or other carriers, and the like.

In some embodiments, active cooling may be applied, for example, by evaporation (e.g., alcohol spray), topical coolant spray (nitrogen), a flow of cooling fluid over the tissue surface, a cooling tube or other carrier, or the like.

In some embodiments and as shown in fig. 1, the digital thermal imager 108 of the system 100 images thermal radiation 150 emitted from the surface of a section of tissue 104. In some embodiments, imager 108 is a video thermal imager configured to generate successive frames of thermal images obtained from the surface of tissue 104 within a field of view (FOV)155 of thermal imager 108 over a set period of time. In some embodiments, the thermal imager 108 comprises a digital microscope thermal imager 108. In some embodiments, the thermal imager 108 may be any suitable digital imager, such as, for example,PI 450 thermal infrared camera from Portsmouth, NH 03801usa. In some embodiments, system 100 includes a visible light camera. In some embodiments, the digital imager 108 includes any suitable thermal sensor, such as an MRI, ultrasound, thermocouple, or any other sensor that measures temperature.

In some embodiments, and as explained in more detail elsewhere herein, the system 100 includes an illumination source 114, the illumination source 114 illuminating the tissue and delineating a surgical boundary for removing cell clusters of abnormal tissue. In some embodiments, and as explained in more detail elsewhere herein, the system 100 includes an ablation energy source 116 to ablate the delineated cell clusters of the abnormal tissue. In some embodiments, the illumination source 114 and the ablation energy source 116 are generated from a single source (e.g., a laser).

Processing of data obtained from individual pixels in a thermal image (frame)

To simplify the description, the following example refers to an IR digital imager. However, as described elsewhere herein, any other suitable thermal imager or sensor may be used.

In some embodiments, the digital thermal imager 108 includes one or more pixel arrays. The pixel array reacts to IR radiation emitted from the imaging surface of the tissue 104. One or more pixel pairs are derived from corresponding sections (S) of the imaging surface of the tissue 104 within the FOV (FOVp) of the pixel_p) The emitted IR radiation reacts. In some embodiments, the heat source 102 is configured to gradually actively heat the surface of the tissue 104 over a set period of time, after which the active heating is stopped and the tissue is allowed to passively cool, during which the tissue temperature returns to the temperature before the active heating begins. Throughout the heating and cooling periods, the thermal imager 108 obtains a series of consecutive frames of thermal images of the surface of the tissue 104. In some embodiments, each successive thermal frame in the acquired series of thermal images is time-stamped, and thus a series of two or more frames acquired over a period of time provides information about the recorded change in the thermal parameter of the tissue. In some embodiments, the system 100 includes a processor 110, the processor 110 configured to process the recorded thermal parameters and map the thermal behavior of the tissue. In some embodiments, and as explained in more detail elsewhere herein, the processor 110 is configured to define a tissue type or state of the imaged tissue based on a thermal behavior map of the imaged tissue.

In some embodiments, the cooling source 102 is configured to gradually actively cool the surface of the tissue 104 over a set period of time, thereafter ceasing the active cooling and allowing the tissue to passively warm up, during which the tissue temperature returns to the temperature before the active cooling begins. Throughout the cooling and warming periods, the thermal imager 108 obtains a series of consecutive frames of thermal images of the surface of the tissue 104.

In some embodiments, each successive thermal frame in the acquired series of thermal images is time-stamped, and thus a series of two or more frames acquired over a period of time provides information about the recorded change in the thermal parameter of the tissue. In some embodiments, the system 100 includes a processor 110, the processor 110 configured to process the recorded thermal parameters and map the thermal behavior of the tissue. In some embodiments, and as explained in more detail elsewhere herein, the processor 110 is configured to define a tissue type or state of the imaged tissue based on a thermal behavior map of the imaged tissue.

In some embodiments, the processor 110 of the thermal imaging system 100 includes a non-transitory computer readable storage medium having a program product embodied therewith. The program product is executable by the processor 110 of the thermal imaging system 100 to process (e.g., compare and render) differences (e.g., differences) between successive timestamp frames expressed by differences between different pixel level values exhibited in at least a portion of tissue within a FOV of the plurality of pixels.

The processor 110 of the thermal imaging system 100 is configured to process pixel level values received from each pixel of each successive image frame according to the timestamp of each frame and generate a graph derived from the pixel level values indicating each location S on the surface of the tissue 104 from within a set period of time_pA change in the emitted IR radiation. The received data represents raster graphics pixel values and/or time-dependent vector pixel values of one or more tissue physiological or pathological parameters at one or more particular points in time.

In some embodiments, the one or more histophysiological or pathological parameters are at least any one of: external parameters that influence the thermal behavior of the cell, e.g., ambient temperature, external heat source and time-dependent thermal gradients between the interior and the environment and the object; and/or intrinsic tissue parameters that influence the thermal behavior (thermal parameters) of the cells, e.g. tissue and/or organism metabolic heat sources, heat loss due to blood perfusion, blood temperature, tissue density, specific heat, thermal conductivity factor, thermal conductivity coefficient, thermal conductivity surface area (m2), temperature of the surface of the object, etc.

In some embodiments, the processor 110 of the thermal imaging system 100 uses one or more algorithms that use various mathematical expressions to approximate the obtained results to values received from one or more imager pixels, and generate variables and/or features based on the pixel level values that can be plotted to generate an accurate map of the imaged tissue type or state.

In some embodiments, the calculated pixel level value-based features are expressed, for example, by a mathematical expression. For illustrative purposes only, in one example, the pixel level value (i.e., the temperature at a pixel at a given time) is expressed by the following mathematical expression, which is based on the Pennes biological thermal conductivity equation:

T(t)＝a+be^ct+dt

where (dt) can be normalized by time and variables (a), (b), (c) and (d) are variables derived from the Pennes biological thermal conductivity equation, which is a widely accepted temperature distribution equation for biological tissue. The variables (a), (b), (c), and (d) are used herein for purposes of clarity and simplicity, by way of example and not limitation, and may include any number or combination of variables and be of any type. For example, the variables (a), (b), (c), and (d) may be at least any one of: external parameters that influence the thermal behavior of the cell, e.g., ambient temperature, external heat source and time-dependent thermal gradients between the interior and the environment and the object; and/or intrinsic tissue parameters that influence the thermal behavior (thermal parameters) of the cells, such as, for example, the source of heat of metabolism of the tissue and/or organism, heat loss due to blood perfusion, blood temperature, tissue density, specific heat, thermal conductivity factor, thermal conductivity coefficient, thermal conductivity surface area (m2), and the temperature of the surface of the object.

In some embodiments, a plurality of features may be calculated based at least in part on the variables (e.g., variables a, b, c, and d), including, but not limited to, features representing various derivative values of the variables, features representing noise in the variables, features based on attenuation equations, features based on fourier series, and related features based on differences in the features.

The following expression includes an example of such a derivation based on the Pennes equation, expressed as:

in some embodiments, the following assumptions are employed:

a) the lateral contribution and/or heat generation is negligible (metabolic time scale one minute [1]) and thus the following expression is obtained:

b)

wherein C is the area and (h) is the heat transfer coefficient, Tc is the core temperature, an

c) We assume that f (t) changes slowly over time.

According to the disclosed assumptions:

wherein

B≈T_i-A

Equation (4.65) in Analytical Bioheat Transfer of the Pennes' Model, Sid M. Becker, Chapter 4 at limit 4. alpha.t. l 2; l- >0 is in accordance with the formula.

T (T ═ 0) can also be approximated by a linear function or a higher order polynomial:

t (t) is expressed as an index of short time periods (e.g., (t) may be between 0 and 40 seconds, between 10 and 30 seconds, between 15 and 25 seconds, or any number of seconds in between).

In another example and in some embodiments, variable (a) may express an initial condition at the transition point from active heating/cooling to passive cooling or warming of the imaged tissue, and is non-time dependent. In some embodiments, the variables (b) and/or (C) express a combination of tissue physiological or pathological parameters, such as density (ρ), specific heat (C), and thermal conductivity (K).

As explained in more detail elsewhere herein, in some embodiments, the extracted variables (a), (b), (c), (d) and other contributing variables, clusters of the same variables, or clusters of variables from one or more thermal images are processed by the computer program product of the processor 110 together with a mathematical expression or combination of mathematical expressions using a data mining process, e.g., to cross-reference data, perform data cleansing and generate output in the form of a graph that indicates and/or identifies various tissue states or types within the imaged tissue region.

In some embodiments, the following is an alternative exemplary expression for a body without an internal heat source:

1.T(t)＝a+be^-ct

2.

wherein:

T_iis the initial temperature of the body.

T ∞ is the ambient temperature.

Parameter(s)

WhereinIs convective thermal conductivity.

Is the thermal conductivity.

3.(normal temperature was used).

In some embodiments, the following is an alternative exemplary expression for a body having an internal heat source:

1.T(t)＝a+be^-ct-dt

2.

3.

4.

where (h) is a convection factor (e.g., the transfer of heat from tissue to air) and is therefore dependent on ambient temperature.

In some embodiments, the computer program product of the processor 110 is configured to compare one or more potential output maps based on each obtained image to a golden standard and to select at least one of: adjusting the analysis process (e.g., by changing selected variables, selected combinations of mathematical calculations, and other mathematical and/or statistical operations), generating an output map expressing the differences between the obtained data and the data of the gold standard, or if no differences exist, not generating an output map.

The curves of the graphs in fig. 2A, 2B, 3, 4, 5A, 5B, 5C, 9B, 12, 14A, 14B, and 15 represent the temperature (T) measured in frames of images per second (FPS)⁰c) Change over time (t). For example, in the case of obtaining images at a rate of 25FPS, one second is represented every 25 frames.

Reference is now made to fig. 2A and 2B, which are graphs of thermal profiles associated with the bio-thermal behavior of heated tissue, in accordance with some embodiments of the present invention. In some embodiments, the curve 200 is based on a time from the surface of the tissue 104 over a set period of time (t 0-t 1)The IR radiation emitted by each Sp on (a) represents a temperature (T) change of the cells within the tissue section (Sp) from the basal temperature (Tb). In some embodiments, curve 200 expresses a biological thermal behavior of the tissue in response to heating over a set period of time (t 0-t 1), and includes a growing portion 202 responsive to heating, a decaying portion 204 during a cooling period of time (t 1-t 2), and a peak temperature 206 at an intersection point (t1) of the growing portion 202 and the decaying portion 204. As explained in more detail elsewhere herein, the time period (t) is set₀To t_n) It is not necessary to reflect that the heating period value is followed by a cooling period and may be broken down into periods that include various temperature change modalities.

As explained in international patent application No. PCT/IL2015/050392 by the same inventor, various states or types of tissue exhibit specific biological thermal behavior expressed by one or more of a specific growth portion 202, a specific decay portion 204, and a specific curve peak temperature 206. In some embodiments, thermal imaging system 100 images tissue for the entire time period (t 0-t 2), and processes data received from pixels of each successive frame of the image according to the timestamp of each frame and generates a growing portion 202 specific to the imaged tissue.

Similarly, in some embodiments, the thermal imaging system 100 processes data received from the pixels of each successive frame of the image according to the timestamp of each frame and generates an attenuation portion 204 specific to the imaged tissue. Thus, the thermal imaging system 100 may combine the particular growing portion 202 and the decaying portion 204, calculate the intersection of the curve portions 202 and 204, and generate a value for each pixel that expresses the location of the peak temperature 206 on the generated curve 200.

As disclosed elsewhere herein, in some embodiments, a method implemented via the system 100 includes actively changing the temperature of the tissue during at least a portion of the imaging period (e.g., t 0-t 1). In some embodiments, the obtained frames provide information about changing tissue physiology or pathology parameters over an imaging session. In some embodiments, actively changing the temperature of the tissue includes actively heating or actively cooling a portion of the tissue during at least a portion of the imaging period.

In some embodiments, data may be extracted from at least some portions of the active heating and active cooling phases, as described elsewhere herein, to improve the accuracy of the output map generated by the computer program product of the processor 110.

For simplicity of illustration, the following examples refer only to method embodiments that include heating followed by cooling. However, all disclosed method embodiments can be implemented in the same manner, with active cooling instead of active heating, e.g., cooling followed by heating.

In some embodiments, the curve 200 generated by the processor 110 of the thermal imaging system 100 is a curve generated from values obtained from a single thermal image pixel over a set period of time (e.g., from a set of consecutive thermal images taken over a set period of time). In some embodiments, the generated curve represents a thermal signature for a particular imaged tissue type or state. In the exemplary embodiment shown in fig. 3, which is a graph of thermal curves associated with the biological thermal response of heated tissue, a pair of thermal response graphs obtained from two pixels P1 and P2 are compared by plotting on the same T/T coordinate system, according to some embodiments of the invention.

As shown in fig. 3, the curve 300 obtained from the pixel P1 steeply grows relative to the curve 300 ' obtained from the pixel P2 and reaches the peak temperature 206 earlier than the peak 206 ' of the curve 300 '. Referring to peak temperature 206 '(e.g., 44.90 ℃) of curve 300', peak temperature 206 is also at a higher temperature (e.g., 45.05 ℃). The difference between the curves 300 and 300 ' is also represented in the decay portions 204 and 204 ', where the decay portion 204 of the curve 300 is steeper relative to the decay portion 204 ' of the curve 300 ', for example reaching a temperature of about 44 ℃ after about 1400 seconds, referring to the decay portion 204 ', which reaches the same temperature after about 1750 seconds. For the sake of simplicity of illustration and in order not to be limited by any example, the temperature (T) in the graph depicted in the drawing is scaled by a continuous natural number.

Similar to the thermal signatures obtained from differences between thermal behavior curves for various tissue states or types, the shape of the thermal behavior curve that results in the peak temperature 206/206' and the decay therefrom also varies between thermal behavior curves and may be identified by the processor 110 of the thermal imaging system 100 as being associated with a particular tissue type or state. In some embodiments, the processor 110 of the thermal imaging system 100 processes values received from at least a portion of the pixel array, as explained in more detail elsewhere herein, and manipulates the values to generate an indication of the tissue state or type in the imaged tissue.

Thus, in some embodiments, the thermal imaging system 100 may identify the thermal behavior curves 300 and 300' as being specific to one or more tissue states or types, and thus may be used to generate outputs indicative of different tissue states or types in the imaged tissue. In some embodiments, the output from the processor 110 of the thermal imaging system 100 may be compiled into a look-up table that associates thermal signatures derived from the thermal behavior graph with specific tissue types or states that may be individually identified and histologically verified.

As disclosed elsewhere herein, differences are consistently exhibited along the thermal behavior curve, and thus, processing portions of variable length (timeline) of the curve are implemented, such as only the increasing portion 202, only the decaying portion 204, only the location of the peak temperature 206, or any portion or combination thereof.

Reference is now made to fig. 4, which is a graph of a thermal profile associated with the biological thermal behavior of heated tissue cells, in accordance with some embodiments of the present invention. Fig. 4 shows an exemplary embodiment in which a pair of thermal behavior curves 400 and 400 'over a time period (T) is obtained from two pixels P3 and P4, and the pair of thermal behavior curves 400 and 400' are compared by plotting on the same T/T coordinate system. The difference between the characteristics of the portions representing curves 400 and 400 'may be defined not only along the location of the growth portion 402/402', the decay portion 404/404 ', and/or the peak temperature 406/406' (as described elsewhere herein), but also between the characteristics representing seasonal noise along the portions.

As shown in the exemplary segment a of fig. 4, there is a difference between the respective curves 404 and 404 ' in terms of the level of seasonal noise 410 and 410 ' measured relative to the mean median of the curves and expressed by phantom lines 450 and 450 ', respectively. In the exemplary embodiment shown in fig. 4, the level of noise 410 of curve 400 relative to the mean median of the thermal behavior curves is greater than the level of noise 410 'of curve 400'. The authors of the present disclosure found that the differences between features based on the noise level relative to the mean median of the thermal behavior curve are specific to tissue type or state and therefore can be used to indicate the presence of different tissue states or types in the imaged tissue.

Reference is now made to fig. 5A, 5B, and 5C (collectively fig. 5), which are graphical illustrations of peak temperature points 206/406 compared by plotting them on the same T/T coordinate system, according to some embodiments of the invention. Peak temperature points 206 and 206 ', respectively, are derived from thermal behavior curve 200/200', and peak temperature points 406 and 406 ', respectively, are derived from thermal behavior curve 400/400', as described elsewhere herein. As shown in the exemplary graph shown in fig. 5, the difference between peak temperatures 206 and 206' is expressed in terms of temperature and/or time to peak temperature. However, the difference between peak temperatures 406 and 406 'is expressed in temperature only, while peak temperatures 406 and 406' are shown arriving at the same time. The processor 110 of the thermal imaging system 100 is configured to identify differences in the coordinates of the peak temperatures 206/206 'and 406/406' and, thus, for indicating the presence of different tissue states or types in the examined tissue.

In some embodiments and as shown in fig. 5C, which is a portion 475 (shown in fig. 4) of an exemplary embodiment of a pair of thermal behavior curves 400 and 400 ' obtained from two pixels P3 and P4, and which pair of thermal behavior curves 400 and 400 ' are compared by plotting on the same T/T coordinate system, the computer program product of processor 110 is configured to compare not only the difference between features based on peak temperatures 206 and 206 ' expressed in temperature and/or time to peak temperature, but also the difference between features based on an analysis of the shape of at least a portion of the graph before the peak (i.e., the increasing portion) and/or a portion of the graph after the peak (e.g., the decreasing portion).

As described elsewhere herein, based on the features representing the peak shape analysis, the computer program product of the processor 110 is configured to identify thermal features on the generated output map that are specific to the tissue type or state imaged within the FOVp of the pixel, e.g., by identifying cell type-specific thermal behavior patterns.

Referring to fig. 3, 4, and 5, in some embodiments, the processor 110 of the thermal imaging system 100 collects values from a plurality of pixels of the imager 108 and groups the results of the calculations, e.g., based on characteristics of one or more of the following: in response to the increasing portion 202 of heating, the decreasing portion 204 during cooling, the peak temperature 206 at the intersection of the increasing portion 202 and the decreasing portion 204, and seasonal noise, and the processor 110 defines a cut-off line between groups that exhibit a close or similar distribution. In some embodiments, and as shown in fig. 5B, which is a plot of the peak temperature points 206/406 for comparison on the same T/T coordinate system, features based on the peak temperature point 206/406 are grouped and identified by the processor 110 of the thermal imaging system 100 as: the early peak groups (502-1, 502-2, 502-3, and 502-4) the late peak groups (504-1, 504-2, 504-3, and 504-4) that peak, for example, below 1000 frames (e.g., 1000 frames are imaged within four seconds at an imaging rate of 25 frames per second) and that are identified as containing normal tissue based on a lookup table generated by the processor 110 of the thermal imaging system 100 (as described elsewhere herein), the late peak groups that peak, for example, only when more than 2000 seconds and that are identified as containing cancerous tissue based on the lookup table.

As shown in fig. 3, 4, and 5, in some embodiments, features representing peak temperature points (such as peak temperature points 206/206 '/506, and 506') may also be identified as thermal features of a particular tissue state or type, and clusters of similar peak temperature points identified by processor 110 of thermal imaging system 100 may indicate clusters of tissue cells sharing the same tissue state in the tissue under examination (e.g., cancerous tissue), as explained in more detail elsewhere herein.

In some embodiments and as disclosed elsewhere herein, the graph is generated and shown by the processor 110 of the thermal imaging system 100. For example, in fig. 3 and 4, the Pennes bio-thermal equation is based, among other things, wherein variables (a), (b), (c), and (d) may be at least any of the following variables, including ambient temperature, external heat source, tissue and/or organism metabolic heat source, heat loss due to blood perfusion, blood temperature, tissue density, specific heat, thermal conductivity factor, thermal conductivity coefficient, thermal conductivity surface area (m2), surface and internal temperature of the subject, and time-dependent thermal gradient between the environment and the subject.

Tissue state and/or type characterization

In some embodiments, the pixel array of the imager 108 images the surface of the tissue 104. In some embodiments, the tissue 104 is preheated. The processor 110 of the thermal imaging system 100 receives and processes the values from each pixel to create a map of the apparent temperature difference over the surface of the object. In some embodiments, each temperature value is assigned a different color. The resulting color matrix is sent to the memory of the processor 110 of the thermal imaging system 100 and to the system display as a thermal map (temperature distribution image) of the surface of the tissue 104.

Reference is now made to fig. 6A, 6B, 6C, and 6D (collectively fig. 6), where fig. 6A is an exemplary thermal image 600 of a portion of mouse skin tissue 104 shown on display 112 of system 100, according to some embodiments of the present invention. As shown in fig. 6A and 6B, thermal image 600 includes thermal map 602. In some embodiments, the region of interest may be examined by moving the pixelblock FOV indicator 604. For example, in fig. 6A and 6B, the pixel group FOV indicator 604 is represented by a square white outline representing the boundary of the aggregate FOV of the pixel groups of the region of interest on the surface of the tissue 104. In some embodiments, the pointer 604 is controlled by, for example, a joystick, a computer mouse, or similar control device. In the exemplary embodiment shown in fig. 6A and 6B, a pixelblock FOV indicator 604 is placed on a section of the surface of the tissue 104 and two foci of abnormal tissue 606 are shown, e.g., suspected of being cancerous.

FIG. 6A illustrates an output graph generated by the computer program product of the processor 110 that employs one or more other combinations of mathematical expressions for the generated output graph illustrated in FIG. 6A based on the extracted feature sets (Fa), (Fb), (Fc), (Fd), i.e., clusters of the same feature sets or clusters of features from the same thermal image illustrated in FIG. 6A. In fig. 6A, two foci of abnormal tissue 606 that are suspected of being cancerous, for example, are identified by the computer program product of the processor 110. In contrast, fig. 6B is a white light image of the same FOV imaged in fig. 6A. In the image of fig. 6B, the regions 606 identified in the generated output map shown in fig. 6A appear the same as the tissue surrounding them. As shown in fig. 6C, the gingival tissue 608 appears as a substantially uniform, uniformly colored gingival tissue in the RGB photograph. In contrast, the thermal diffusion map of FIG. 6D delineates a large section 610 of abnormal gum tissue relative to surrounding normal tissue 612. In this particular example, abnormal gingival tissue is identified as cancerous tissue.

In some embodiments, and as shown in fig. 6C and 6D, the figure is an RGB photograph of a human gum (fig. 6C) and a processed and generated thermal diffusion map superimposed on the RGB photograph of the tissue (fig. 6D).

In some embodiments, a method for differentiating tissue states or types includes: actively changing the temperature of the surface of at least a portion of the tissue from a base temperature (Tb) for a predetermined first time period (t 0-t 1), then ceasing to effect the temperature change, and allowing the temperature of the tissue to passively return to the base temperature for a second time period (t 1-t 2), while obtaining a plurality of thermal images of the imaged surface of the tissue during the first and second time periods (t 0-t 2).

In some embodiments, the method comprises: processing the thermal values received from the pixels of the imager 108 to generate one or more values associated with one or more physiological or pathological parameters of the tissue; comparing the values to a database (e.g., a look-up table of signature data associated with one or more tissue states or types); and generating an output indicative of an identification of a tissue state or type of the tissue cells and/or a division of boundaries of identified regions of tissue cells in the same tissue state on the obtained image.

In some embodiments, indicating and/or identifying an organizational state or type includes one or more of: tracking changes over time of thermal values received from imager pixels, identifying patterns of the changes, and classifying or grouping the changed patterns into categories or groups. The classified patterns are then compared to signature patterns of tissue states or types, each category is associated with a database of predetermined signature patterns of tissue states or types, and regions containing tissue in the identified tissue states or types are identified within the thermal image obtained by the identification of tissue states or types and/or association.

The following is one example of the above-described method for distinguishing tissue states or types. Reference is now made to fig. 7, which is an exemplary simplified flowchart illustrating operation of processor 110 of thermal imaging system 100 according to some embodiments of the invention. As shown in fig. 7, at 702, the processor 110 of the thermal imaging system 100 is configured to acquire a sequence of thermal images of the surface of the tissue 104 from the imager 108 over a period of time.

In some embodiments, and as explained elsewhere herein, the processor 110 of the thermal imaging system 100 is configured to extract one or more variables (a), (b), (c), and (d) derived from the Pennes biological thermal conductivity equation at 703 and/or derive one or more variables (a), (b), (c), and (d) from at least any one of: external parameters that influence the thermal behavior of the cell, e.g., ambient temperature, external heat source and time-dependent thermal gradients between the interior and the environment and the object; and/or intrinsic tissue parameters that influence the thermal behavior (thermal parameters) of the cells, such as, for example, the source of heat of metabolism of the tissue and/or organism, heat loss due to blood perfusion, blood temperature, tissue density, specific heat, thermal conductivity factor, thermal conductivity coefficient, thermal conductivity surface area (m2), and the temperature of the surface of the object.

In some embodiments, the processor 110 of the thermal imaging system 100 is configured to segment the tissue into segments including locations having corresponding one or more thermal variables, and optionally generate an output indicative of the tissue segments, at 704.

Optionally, at 705, the processor 110 of the thermal imaging system 100 is configured to calculate one or more features of each pixel, e.g., (Fa), (Fb), (Fc), and (Fd), based on the one or more extracted variables (a), (b), (c), and/or (d). In some embodiments, and as explained elsewhere herein, the calculated features (Fa), (Fb), (Fc), and (Fd) represent thermal behavior of the imaged tissue cells affected at least in part by the thermal parameter, as listed elsewhere herein. In some embodiments and as shown in fig. 6, processor 110 of thermal imaging system 100 displays the calculated features of at least features (Fa), (Fb), (Fc), and (Fd) on display 600, for example, in the form of list 608 or a graph depicting the distribution of the calculated features (Fa), (Fb), (Fc), and (Fd) in the imaging region.

At 706, the processor 110 of the thermal imaging system 100 compiles the set of one or more features calculated at step 705 from each pixel within the FOV of the imager 108 and processes for each set of one or more features (Fa), (Fb), (Fc), and (Fd), and generates a difference map (VFa, VFb, VFc, and VFd) for each set or group compiled at 706 at 708.

As described elsewhere herein, the computed features (Fa), (Fb), (Fc), (Fd) and other contributing features, sets of the same features, or sets of features from one or more thermal images are processed by the computer program product of the processor 110 using a data mining process, e.g., to cross-reference data, perform data cleansing and generate output in the form of a graph that indicates and/or identifies various tissue states or types within the imaged tissue region.

In the exemplary embodiment shown in fig. 6, processor 110 of thermal imaging system 100 displays on display 600 an output map generated by a computer program product of processor 110 showing at least the calculated differences in the values of features (Fa), (Fb), (Fc), and (Fd) as list 610.

In some embodiments and optionally and as shown in fig. 7, at 710, each compiled set of difference maps (VFa, VFb, VFc, and VFd) at 706 of at least the features (Fa), (Fb), (Fc) above the FOV of the imager 108 is displayed on, for example, the display 600 in sequence (at 710) or in any combination (e.g., one or more superimposed on each other) (at 712) or in any combination and superimposed on the RGB image of the FOV of the imager 108 (at 714) to identify abnormal tissue (e.g., cancerous tissue) according to a look-up table based on a predetermined golden standard reference, which increases the accuracy of the thermal image analysis process.

In some embodiments and optionally, the processor 110 of the thermal imaging system 100 calculates 716 cross-sectional points of one or more data sets, e.g., differences (VFa, VFb, VFc, and VFd) between the feature sets generated 708, and identifies 718 one or more groups of pixels having close or similar calculated cross-sectional points. At 720, the processor 110 of the thermal imaging system 100 generates a map corresponding to the locations of the identified pixel groups from which analysis of the obtained values results in cross-sectional points that are closest to the values, variables and/or features defined by the predetermined gold standard reference, and at 722 and 724, the processor 110 of the thermal imaging system 100 superimposes the map generated at 720 on the RGB image of the FOV of the imager 108 to assist the health professional in identifying the locations of the suspicious cell clusters on the surface of the tissue 104.

In some embodiments, the cross-sectional points of the one or more datasets (e.g., the difference datasets (VFa, VFb, VFc, and VFd)) identified by the processor 110 of the thermal imaging system 100 correspond to consistent regions in the overlay of the difference datasets (VFa, VFb, VFc, and VFd). In some embodiments, and as explained elsewhere herein, the system 100 includes an illumination source 114, the illumination source 114 illuminating tissue and delineating a surgical boundary for removing abnormal tissue. Alternatively or additionally and optionally, in some embodiments, the system 100 includes an ablation energy source 116 to ablate the delineated abnormal tissue. In some embodiments and optionally, at 724, the processor 110 of the thermal imaging system 100 identifies the location of the suspicious cell clusters on the surface of the tissue 104 and provides contour coordinates of the suspicious cell clusters to the illumination source 114 that demarcates the surgical boundary to remove the abnormal tissue and/or to the ablation energy source 116 that applies ablation energy 116 to ablate the demarcated abnormal tissue.

Returning to the exemplary embodiment shown in FIG. 6, the screen image 600 of the display 112 of the system 100 displays the paxel FOV at a particular set of coordinates (position: 141,270) that are displayed within the square white outline 604. In some embodiments, the frame 604 is located (position: 141,270) to identify the suspect abnormal tissue mass 608 as cancerous or non-cancerous, for example.

In some embodiments, the method includes performing a rapid shallow thermal scan over a large area and identifying suspicious foci, and then carefully and carefully imaging the suspicious foci or cellular regions by placing at least a portion of the regions within the square white outline 604.

In some embodiments, screen image pixel cluster 606/608 represents a cluster of pixels (and thus a cluster of imaged tissue cells) that share one or more characteristics, including differences calculated by processor 110 of thermal imaging system 100 relative to surrounding pixels (and thus imaged tissue) based on one or more variables (a), (b), (c), and (d), as described elsewhere herein.

In some embodiments, and as explained elsewhere herein, a difference map generated for each isolated value of predetermined features (Fa), (Fb), (Fc), and (Fd), or any combination thereof, within the imager FOV is superimposed on the RGB image of the imaged tissue to allow the naked eye to identify suspicious cell clusters.

In some embodiments, the present disclosure may provide for implementing machine learning algorithms and/or techniques, for example, for determining tissue state. In some embodiments, in a training phase, an example machine learning classifier of the present disclosure may be configured to receive, obtain, and/or otherwise have received or obtained a data set comprising a plurality of tissue thermal parameters, features, and/or variables related to a plurality of subjects. In some embodiments, these thermal parameters, characteristics, and/or variables are the same or substantially similar to those described in sufficient detail elsewhere herein.

In some embodiments, the pre-processing stage may include data preparation. Data preparation may include cleaning up data, converting data, and/or selecting a subset of records. In some embodiments, data preparation may include performing pre-processing operations on the data. For example, an interpolation algorithm may be performed to generate values for missing data. Upsampling and/or predictor level transformation (e.g., for variable selection) may be performed to accommodate class imbalance and non-normality in the data. In some embodiments, performing the interpolation algorithm includes interpolating or estimating values of missing data, such as by generating a distribution of available data having clinical parameters of the missing data, and interpolating values of the missing data based on the distribution.

In some embodiments, the time processing step may be configured to generate a time-dependent representation of one or more parameters, features, and/or variables using, for example, fourier transforms, polynomial adjustments, attenuation equations, and/or various statistical tools. In some embodiments, the temporal processing step may include automatically and/or manually combining a plurality of measurements obtained from the subject over a sequence of time periods to determine and/or create at least one combined parameter and/or feature that may represent a pattern of change in the plurality of measurements over time and/or a time series variable.

In some embodiments, the feature extraction step may be configured to generate additional features, for example based on relationships between existing features in the dataset, and add the additional features to the dataset.

In some embodiments, variable selection may be performed to identify the most relevant variables and predictors, for example, from the obtained set of parameters. In some embodiments, the variables and/or variable selections may include executing supervised machine learning algorithms, such as constraint-based algorithms, constraint-based structure learning algorithms, and/or constraint-based local discovery learning algorithms. In some embodiments, variable selection may be performed to identify a subset of variables in the training data that have a desired predictive capability relative to the rest of the variables in the training data, thereby enabling more efficient and accurate predictions using a model generated based on the selected variables. In some embodiments, the variable selection is performed using a machine learning algorithm, for example, a variance analysis (ANOVA), lifting integration (such as XGBoost), growth contraction ("gs"), delta association markov blanket ("iamb"), fast delta association ("fast, iamb"), maximum minimum parent-child ("mmpc"), or semi-staggered Hiton-PC ("si. However, various other embodiments of such machine learning algorithms may be used to perform variable selection and other processes described herein. In some embodiments, variable selection may search for smaller sized variable sets that attempt to represent the underlying distribution of the entire variable set, which attempts to increase generalization to other data sets from the same distribution.

In some embodiments, variable selection may be performed by removing highly correlated variables. Several algorithms can be used to search the input data set with ranked predictors to find a reduced set of variables that best represents the underlying distribution of all variables for the infectious complication outcome. A variable selection filtering algorithm may be used to select the reduced set of variables. For example, in some embodiments, one or more of a maximum-minimum parent-child (mmpc) and/or inter-iamb algorithm may be used to select a node of a corresponding bayesian network as the reduced set of variables.

In some embodiments, variable selection is performed to search the training data for a subset of variables that serve as nodes of the bayesian network. A bayesian network (e.g., belief network, bayesian belief network) is a probabilistic model that uses directed acyclic graphs to represent a set of variables and their conditional dependencies. For example, in the context of diagnostic prediction, variable selection may be used to select variables from training data to use as nodes of a bayesian network; given the value of a node for a particular subject, a prediction of the diagnosis of that subject may be generated.

In some embodiments, a training data set for a machine learning classification model of the present disclosure is created based at least in part on the collected parameters and the variable selection process performed as described above. In some embodiments, the training data set includes a set of parameters, features, and/or variables associated with various tissue states or types of the subject. Values of the parameters may be received and stored for each subject of the plurality of subjects. The training data set may associate values of a plurality of parameters, features, and/or variables with a corresponding tissue state for each subject of the plurality of subjects. In some embodiments, the set of parameters, characteristics, and/or variables may be labeled with a corresponding tissue state.

In some embodiments, the machine learning classifier of the present disclosure is trained on a training data set to generate a classification model. For example, the machine learning classifier may perform a classification algorithm (e.g., a binary classification algorithm) on each subset of model parameters to generate the prediction of the tissue state. In some embodiments, the classification algorithms include, but are not limited to, linear discriminant analysis (lDA), classification and regression trees (CART), nearest neighbor (KNN), Support Vector Machine (SVM), Gaussian Support Vector Machine (GSVM), logistic regression (GLM), Random Forest (RF), Generalized Linear Model (GLMNET), and/or Naive Bayes (NB). In some embodiments, classification may be defined as a task that summarizes a known structure to be applied to new data. Classification algorithms may include linear discriminant analysis, classification and regression trees/decision tree learning/random forest modeling, nearest neighbor, support vector machines, logistic regression, generalized linear models, naive bayes classification, neural networks, and the like. In some embodiments, the trained machine-learned classification models of the present disclosure may include, for example, cluster analysis, regression (e.g., linear and non-linear), classification, decision analysis, and/or time series analysis, among others. In some embodiments, where variable selection is performed prior to generating the random forest model, the training data is sampled based on a reduced set of variables from the variable selection (as opposed to sampling based on all variables).

In some embodiments, after the training phase, the trained machine learning classifier of the present disclosure may be configured to implement a validation process, e.g., by a first evaluation, which may include, e.g., cross-validation. Cross-validation may be configured to randomly divide the training set into, for example, ten shares. Ten validation may then be run ten times, for example, using nine different copies of the training set for machine learning modeling and the tenth copy for validation. The results may be assessed by calculating statistical measures, such as the mean and confidence interval of the area under the receiver operating property curve (AUROC) for ten different assessments. In some embodiments, the second evaluation may include an assessment of the machine learning model with respect to a validation set (e.g., may include the tenth part of the 10% of the raw data for validation). In some embodiments, the third evaluation may include statistical analysis, for example, including presenting population characteristics by skewing median and quartile spacing (IQR) of the data, and for normal distribution data, by mean of standard deviation (e.g., using bootstrap techniques). In some embodiments, the cross-validation process of the machine learning model may implement a statistical method configured to estimate the skills of the machine learning model for limited data samples, e.g., to estimate how the machine learning model is expected to perform when used to predict data not used in training the machine learning model. In some embodiments, the cross-validation process of the machine learning model may include dividing a given data sample into a plurality of groups and/or shares, such as ten groups and/or shares.

In some embodiments, the trained machine learning classifier of the present disclosure may be applied to the received thermal video stream of tissue in an inference stage to generate one or more predictions about the state of a region within the tissue.

In some embodiments, an unsupervised classification model may be employed, for example, to extract parameters, features, and/or variables from a thermal image stream of tissue in an unsupervised manner. In some embodiments, such extracted parameters, features, and/or variables may then be used as input to the trained machine learning classifier described above.

Reference is now made to fig. 8A and 8B, which are simplified graphs illustrating a difference data set or group of cross-sectional points according to some embodiments of the invention. In some embodiments, the processor 110 is configured to select and process differences in pixel level values or sets of thermal variables or features based on pixel level values (such as the sets shown in fig. 8A and 8B) that are closest to the values of pixel level values, thermal variables or features defined by the predetermined gold standard reference. As shown in the exemplary graph shown in FIG. 8, the cross-sectional points 802 and 804 are clustered into one or more clusters (e.g., 802-1, 802-2, 802-3, and 802-4 and/or 804-1, 804-2, 804-3, and 804-4).

As explained elsewhere herein, the processor 110 of the thermal imaging system 100 is configured to identify associated pixels having generated cross-sectional points 802 and 804, and delineate a boundary 850 between a first type of tissue associated with the cross-sectional point 802 in a segment 855 on the surface of the tissue 104 and a second type of tissue associated with the cross-sectional point 804 in a segment 860 on the surface of the tissue 104. The states or types of histologically identified tissues 802 and 804 are registered in a look-up table stored in the memory of the processor 110 of the thermal imaging system 100 for future reference.

Alternatively and optionally, in some embodiments, processor 110 of thermal imaging system 100 is configured to compare cluster 802/804 to a pre-compiled lookup table, identify tissue state or type 802 as a first type of tissue (e.g., healthy tissue) in tissue segment 855, and identify tissue state or type 804 as a second type of tissue (e.g., cancerous tissue) in tissue segment 860, and delineate boundary 850 between tissue segments 855 and 860. Additionally and optionally, in some embodiments, the processor 110 of the thermal imaging system 100 is configured to render the identified tissue states or types 802 and 804 and display the map on the display 112 superimposed on the RGB image of the FOV of the imager 108, as shown in fig. 8B.

Heat application technique

Vector heating

As used herein, the term "vector" heating refers to heating along a path that may follow any pattern and not necessarily along a straight line.

Reference is now made to fig. 9A, which is a simplified illustration of a plan view of a thermal distribution over a portion of a surface, according to some embodiments of the invention; and fig. 9B, which is a thermal profile of tissue within a portion of a tissue surface according to some embodiments of the invention.

As shown in the exemplary embodiment illustrated in FIG. 9A, the tissue surface is heated along a line 902 disposed on one side of the suspected abnormality 904. For clarity of explanation, the heat distribution from line 902 in a direction away from the suspect tissue anomaly is ignored.

In some embodiments, the thermal imaging system 100 is configured to obtain multiple thermal images of the FOV of the imager 108 over a set time period (t), and process successive frames of the multiple images to extract information about differences in thermal parameters of tissue cells over the set time period.

In some embodiments, the thermal imaging system 100 compares the rate of thermal diffusion through tissue cells within the FOV of the imager 108 in the direction indicated by arrow 906 over one or more time periods (e.g., t1, t2, t3, t4) measured from the heat application time (t 0). In some embodiments, temperature measurements over time periods (t1), (t2), (t3), and (t4) are taken along lines parallel to the heater line 902 (e.g., L1, L2, L3, and L4).

As shown in the embodiment illustrated in fig. 9A, during the time period (t3), the heat generated by the line 902 is uniformly distributed over a majority of the surface of the tissue 104 within the FOV of the imager 108. However, measurements within region 970 depicted by the dashed circles show that heat diffusion through tissue cells within this region is slower compared to most of the surface of tissue 104 (including depicted regions 950 and 960 on either side of region 970). The processor 110 of the thermal imaging system 100 is configured to identify differences in the rate of diffusion of tissue cells through the region 970 as being associated with differences in one or more physiological or pathological/thermal parameters associated with the tissue within the region 907 and the surrounding tissue, and to label the region 970 as containing tissue suspected of being abnormal (e.g., cancerous).

Additionally and optionally, in some embodiments and as explained in more detail elsewhere herein, the processor 110 of the thermal imaging system 100 is configured to process a thermal profile of tissue within the FOV of the imager 108. As shown in the exemplary embodiment illustrated in fig. 9B, which is a graph of a thermal profile associated with a biological thermal behavior of heated tissue, curve 955/965 represents a thermal profile of tissue surrounding suspect tissue within region 970 (e.g., tissue in regions 950 and/or 960) where curve 975 represents a thermal profile obtained from tissue within region 970, according to some embodiments of the present invention.

The graph displayed by processor 110 of thermal imaging system 100 shows that the overall thermal behavior (i.e., response to heating) of the tissue cells within region 970 is slower than the thermal behavior (i.e., response to heating) of the tissue cells within the region surrounding region 970 (e.g., region 950/960). This is indicated, for example, by the shallow growth portion 972 of curve 975 relative to the steeper growth portion 952/962 of curve 955/965 in response to heating. Additionally and optionally, curve 975 reaches peak temperature 976 later than curve 955/965, indicating slower thermal behavior of tissue within region 970. Similar to the shallow growing portion 972, the decaying portion 974 exhibits slower thermal behavior of tissue within the region 970 indicated by the shallow curve relative to the decaying portion 954/964 of the curve 955/965.

In some embodiments and as explained in more detail elsewhere herein, the processor 110 of the thermal imaging system 100 is configured to process the differences exhibited all the way along the thermal behavior curves 975 and 955/965 by processing and comparing the graphs as a whole or processing only portions of the curves (such as only the growth portions 972 and 952/962, only the decay portions 974 and 954/964, only the locations of the peak temperatures 976 and 956/966, or any combination thereof) and generate a thermal signature derived from the difference between the thermal behavior curves 975 and 955/965 (the difference being represented by the shape of the thermal behavior curves before and decaying from the peak temperatures), and identify a particular tissue state or type associated with the thermal signature. In some embodiments, the processor 110 of the thermal imaging system 100 processes information received from at least a portion of the pixel array, as explained in more detail herein, and uses this information to indicate the presence of different tissue states or types (e.g., normal versus cancerous) in the tissue under examination.

In some embodiments, the accuracy and specificity of tissue type or state identification may be increased by heating the surface of the tissue 104 along one or more lines 902 disposed to one side of the suspected abnormal tissue 904. In the exemplary embodiment depicted in fig. 10A, 10B, and 10C, which is a simplified illustration of a plan view of a thermal distribution over a portion of a tissue surface, heating the surface of tissue 104 along line 902/1002 disposed to one side of suspected abnormal tissue 904, according to some embodiments of the invention. In some embodiments, line 902 (fig. 10A) and line 1002 (fig. 10B) are perpendicular to each other.

As shown in fig. 10C, the processor 110 of the thermal imaging system 100 is configured to compile thermal behavior data obtained from the thermal images 1004 and 1006 shown in corresponding fig. 10A and 10B, extract information about one or more physiological or pathological thermal parameters associated with cells identified as abnormal tissue cells in the thermal images 1004 and 1006 primarily within the region 1008, and generate at least a contour of the suspect abnormal tissue 904.

In some embodiments, the duality of at least a portion of the values obtained by the processor 110 of the thermal imaging system 100 and the comparison between the values obtained from the image 1004 and the values obtained from the image 1006 increase the accuracy and specificity of tissue type or state identification and localization. This enables the processor 110 of the thermal imaging system 100 to zoom in (i.e., zoom in to display) the region 1008 shown in fig. 10C and more accurately delineate the outline 1012 of the suspect abnormality 904. In some embodiments, the processor 110 of the thermal imaging system 100 is configured to superimpose the contour of the suspicious abnormal tissue 904 onto the RGB image of the surface of the tissue 104 to assist a health professional in clearly and accurately identifying the boundaries of the suspicious cell clusters 904 on the surface of the tissue 104.

One example for using vector heating is in tissue boundary analysis, as shown in fig. 11A and 11B, which are simplified illustrations of a plan view of a thermal profile over a portion of a tissue surface, according to some embodiments of the invention. In the exemplary embodiment shown in FIG. 11A, the surface of the tissue 104 includes two boundary regions 1102 and 1104 that are separated by a boundary line 1106 and appear to include different tissue states, such as one or more blobs 1108 or tissue types.

As shown in the exemplary embodiment depicted in FIG. 11A, the surface of the tissue 104 is heated to one side of the suspicious spot 1112 along a line 1110 disposed substantially on the boundary 1106 between the regions 1102 and 1104. For clarity of explanation, the heat distribution from the line 902 in a direction away from the suspect spot is ignored.

To increase the resolution and accuracy of abnormal cell identification, the FOV of the imager 108 is limited to the region 1114 of the surface of the tissue 104. The processor 110 of the thermal imaging system 100 is configured to obtain thermal values from an array of pixels imaging the FOV of the imager 108 and process the obtained values, as explained elsewhere herein. In some embodiments and as shown in the exemplary embodiment depicted in fig. 11B, processor 110 of thermal imaging system 100 generates map 1150 identifying tissue segment 1112 as abnormal tissue (e.g., cancerous tissue) by marking tissue segment 1112 by identifying colors or contours within the surface of tissue 104 of border regions 1102 and 1104 as normal.

Random point heating

Reference is now made to fig. 12, which is a simplified graphical and plan view illustration of a thermal profile over a portion of a tissue surface, according to some embodiments of the invention. In some embodiments and as shown in fig. 12, the heat source 102 heats a randomly sized portion 1202 of the surface of the tissue 104. In some embodiments, randomly sized portions 1202 are heated continuously and uniformly, for example, by applying the same level of heat (e.g., joules) during equal periods of time, and successive thermal images are taken at given time intervals by the imager 108 of the thermal imaging system 100.

In some embodiments, and as explained elsewhere herein, the processor 110 of the thermal imaging system 100 processes the obtained images to identify and delineate the tissue segment 1212. For example, in some embodiments, the processor 110 is configured to process and identify temporal temperature uniformity (t)_u) At which a majority (Mc%) of the surface of the tissue 104 is imaged to be at the same temperature. In some embodiments, a majority of the tissue (Mc%) of the surface of the tissue 104 is defined by a percentage of the area of the surface of the tissue 104 within the FOV of the imager 108, e.g., (Mc%) is over 50%, between 50% -99%, 60% -90%, and 70% -80%. In some embodiments, the processor 110 is at the end point (t)_u) A heat map 1250 is generated to identify the abnormal tissue section 1212.

The exemplary graph depicted in FIG. 12 shows (t) along an arbitrary line Q-Q above the surface of the tissue 104_u) A curve 1204 of the temperature levels at. Such asFIG. 12 shows that graph 1204 shows a substantially uniform temperature of the tissue along line Q-Q, except for the lower temperature length between L1 and L2. In some embodiments, the lower temperature reached by the tissue along the portion L1-L2 of line Q-Q may indicate that the tissue includes a slower growing portion of the thermal curve, as explained in detail elsewhere herein, thereby identifying the tissue as abnormal cells. In some embodiments and as described elsewhere herein, processor 110 of thermal imager 100 processes successive thermal images of the abnormal tissue in the L1-L2 section of line Q-Q and processes the growing portion of the thermal profile and identifies the type of abnormal tissue (e.g., cancer cells).

As shown in FIG. 13, which is an exemplary simplified flow chart illustrating operation of processor 110 of thermal imaging system 100 according to some embodiments of the invention, processor 110 is configured to obtain at 1302 a slave (t) of₀) To (t)_u) A thermal image from the imager 108 acquired over a time period of (a), and identified at (t) at 1304_u) A cluster of cells (e.g., tissue section 1212) having a lower temperature than a majority (Mc%) of the tissue 104 surface. At 1306, the processor generates a thermal map of the surface of the tissue 104 within the FOV of the imager 108 that identifies or depicts a cluster of abnormal tissue sections 1212. In some embodiments and optionally, at 1308, the processor 110 superimposes the map generated at 1306 on the RGB image of the surface of the tissue 104 and delineates or ablates the abnormal tissue 112 at 1310.

In some embodiments and at 1312, the processor 110 is configured to process the growing portion of the thermal profile of the cell clusters identified at 1304, and identify at (t) at 1314_u) The tissue type or state (e.g., cancerous) of the tissue section 1212 having a lower temperature than a majority (Mc%) of the surface of the tissue 104.

Pulsed application of heat

In some embodiments and as shown in fig. 14A and 14B, which are graphs of thermal profiles associated with the biological thermal behavior of heated tissue, the surface of the tissue 104 is heated over a period of time by a plurality of heating pulses, in accordance with some embodiments of the present invention. In some embodiments, the heat pulses are applied continuously and uniformly, for example, by applying the same level of heat (e.g., joules) at equal intervals between heat pulses during equal time periods. The processor 110 of the thermal imaging system 100 is configured to obtain a plurality of sequential thermal images from the imager 108 and to process the thermal behavior of the tissue of the surface of the tissue 104 in response to the heating pulse.

In some embodiments, as shown in fig. 14A and 14B and explained in more detail elsewhere herein, different states or types of tissue exhibit different thermal behavior in response to the applied pulsed heat, as expressed by differences in thermal profiles associated with the thermal behavior. In one example, as shown in fig. 14A, a thermal parameter obtained from imaged tissue exposed to pulsed heat over a period of time and processed by the thermal imaging system processor 110 exhibits a curve 1402 including one or more increasing portions 1404, each followed by one or more decreasing portions 1406 and a plurality of temperature peak points 1408.

In some embodiments, the processor 110 is configured to perform a top analysis on the curve 1402 and identify a thermal signature of the tissue type or state imaged within the pixel-specific FOVp based on the analysis, e.g., by identifying temperature peaks (e.g., P1, P2, P3, and P4) of the continuous curve in response to successive heating pulses at a given time (e.g., t1, t2, t3, and t4), and processing relationships between peaks, e.g., time intervals between peaks (e.g., i1, i2, i3, and i4), or a calculated linear regression 1450 of the increase in the peaks.

In some embodiments, the processor 110 of the thermal imaging system 100 is configured to perform a comparative analysis on only selected portions of the thermal profile (e.g., the growth portion, the decay portion, and/or the peak temperature at the intersection of the growth portion and the decay portion), such as the exemplary graph shown in fig. 14B, that exhibit increasing delay periods of the profiles 1412, 1414, and 1416 in response to successive heat pulses, i.e., d1 between t1 and t1 ', d2 between t2 and t2 ', and d3 between d3 and t3 '. In some embodiments, the processor 110 is configured to identify a thermal signature specific to a tissue type or state imaged within the FOVp of the pixel based on the analysis, such as by identifying a thermal behavior pattern specific to the tissue type or state.

Staged heating

In some embodiments and as shown in fig. 15, which is a graph of a thermal profile associated with the biological thermal behavior of heated tissue, the surface of the tissue 104 is heated in sections (fractional) according to some embodiments of the invention. In some embodiments, heat is applied by multiple pulses (e.g., same level of heat or joules) set at predetermined intervals (e.g., equal or varying lengths), and the imager 108 of the thermal imaging system 100 obtains successive thermal images throughout the growing portion 1502 of the obtained thermal profile 1500.

In the exemplary embodiment shown in fig. 15, three heating pulses are applied at three time points tP1, tP2, and tP3, resulting in a step-wise increasing portion 1502 of curve 1500 having three segments (fractions) Δ T1, Δ T2, and Δ T3. A potential advantage of segmented heating is that segmentation of the growing portion 1502 is analyzed rather than the entire growing portion 1500, allowing for increased resolution and accuracy of abnormal cell identification. In some embodiments, differences between tissue states or types are only expressed in differences within only one of the segments Δ T1, Δ T2, and Δ T3, thereby providing higher resolution of tissue type signature patterns and increasing the accuracy and specificity of tissue type or state identification.

3D heating

Reference is now made to fig. 16A and 16B, which are simplified illustrations of cross-sectional views of thermal distributions within portions of a tissue surface, according to some embodiments of the invention. In some embodiments, a volume of tissue 1602 below the surface of the tissue 104 is heated along a plane 1604 using a three-dimensional heating system, such as ultrasound, laser, IR or RF radiation applied at varying frequencies in a direction from the surface into deeper tissue, indicated by arrow 1675, along a wire 1650 disposed on one side of the suspected abnormal tissue 1606.

As shown in fig. 16A and 16B, thermal distribution within the portion 1602 below the surface of the tissue 104 occurs along lines 1608. For clarity of explanation, the thermal distribution from the plane 1604 in a direction away from the suspect tissue section 1606 is ignored.

In some embodiments, the processor 110 of the imaging system 100 is configured to process a plurality of thermal images taken by a 3D thermal imaging system (e.g., MRI, CT scanner, ultrasound transceiver, RF transceiver, or the like) simultaneously or sequentially at varying spatial orientations relative to the surface of the tissue 104 along one or more planes. In the exemplary embodiment shown in fig. 16, multiple thermal images taken by the 3D thermal imaging system are acquired simultaneously or sequentially along multiple planes oriented spatially parallel (plane 1608) and/or perpendicular (plane 1610) relative to the surface of the tissue 104.

As shown in fig. 16B and in some embodiments, the processor 110 of the thermal imaging system 100 is configured to compile thermal behavior values obtained from thermal images taken along the plurality of planes 1608 and/or the planes 1610, and as explained in more detail elsewhere herein, extract information about one or more physiological or pathological thermal parameters related to tissue identified as abnormal tissue cells 1606 in the one or more obtained thermal images, and generate at least a three-dimensional contour of the suspected abnormal tissue 1606.

In some embodiments, the duality of at least a portion of the values obtained by the processor 110 of the thermal imaging system 100 and the comparison between the obtained values from the obtained images improves the accuracy and specificity of tissue type identification and localization within the tissue under the surface of the tissue 104. In some embodiments, the processor 110 of the thermal imaging system 100 is configured to superimpose a 3D contour of the suspicious abnormal tissue 1606 onto an RGB 3D image of the tissue below the surface of the tissue 104 to assist a health professional in clearly and accurately identifying the boundaries of the suspicious cell clusters 904 within the tissue.

Throughout this application, various embodiments of the present invention may be presented in a range format. It is to be understood that the description of the range format is merely for convenience and brevity and should not be construed as an inflexible limitation on the scope of the invention. Accordingly, the description of a range should be considered to have explicitly disclosed all the possible sub-ranges as well as individual values within that range. For example, description of a range (such as from 1 to 6) should be considered to have explicitly disclosed sub-ranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6, etc., as well as individual numbers within that range, e.g., 1,2, 3, 4, 5, and 6. This applies regardless of the breadth of the range.

Whenever a numerical range is indicated herein, it is intended to include any reference number (fractional or integer) within the indicated range. The phrases "range/range between a first indicated digit and a second indicated digit" and "range/range from a first indicated digit to a second indicated digit" are used interchangeably herein and are intended to include the first indicated digit and the second indicated digit and all fractions and integers therebetween.

In the description and claims of this application, each of the words "comprising," "including," and "having" and forms thereof are not necessarily limited to members of a list that may be associated with the words. In addition, where there is inconsistency between the present application and any of the documents incorporated by reference, the present application shall control.

Disclosed herein are methods and computer program products that can automatically construct (i.e., without human intervention) a list of relevant claims and supporting evidence given the subject matter under consideration (TUC). Thus, for example, a person may draw convincing claims to support his or her opinion, as well as prepare another party for a counter claim that may be raised when discussing a TUC.

The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions thereon for causing a processor to perform aspects of the invention.

The computer-readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer-readable storage medium includes the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanically coded device such as a punch card or a raised pattern in a groove with instructions recorded thereon, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium should not be construed as a transitory signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., optical pulses traveling through a fiber optic cable), or an electrical signal transmitted through an electrical wire.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a corresponding computing/processing device, or to an external computer or external storage device, via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

Computer-readable program instructions for carrying out operations of the present invention may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state-setting data, or source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + +, or the like, and a conventional procedural programming language such as the "C" programming language or a similar programming language. Or the connection may be made to an external computer (for example, through the internet using an internet service provider). In some embodiments, an electronic circuit comprising, for example, a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), may personalize the electronic circuit by executing computer-readable program instructions with state information of the computer-readable program instructions to perform aspects of the present invention.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable storage medium having the instructions stored therein comprise an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The description of various embodiments of the present invention has been presented for purposes of illustration but is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques found in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.