阅读说明：本技术 骨龄评估装置、方法以及用于记录程序的记录介质 (Bone age assessment device, method, and recording medium for recording program ) 是由 陈东奎 于 2018-09-04 设计创作，主要内容包括：提出了一种骨龄导出装置。根据本公开,该装置可以：从通过对通过拍摄人体的输入图像进行分割而形成的多个分割图像确定多个人体部位当中的第一人体部位的最高优先顺序的第一分割图像；基于从所述输入图像的全部像素导出的基准值,对所述第一分割图像的多个第一像素中的每一个进行处理；从基准图像集中选择针对所述第一人体部位的第一基准图像；基于所述第一分割图像的按照所述基准值处理后的所述第一像素和所述第一基准图像的与所述第一像素对应的第二像素之间的运算结果,确定是否存在与所述第一基准图像匹配的部分区域；基于所述第一基准图像,确定由所述部分区域呈现的所述第一人体部位的骨龄等级；并且基于所述骨龄等级导出所述人体的骨龄。(A bone age deriving device is provided. According to the present disclosure, the apparatus may: determining a first divided image of a highest priority order of a first human body part among a plurality of human body parts from a plurality of divided images formed by dividing an input image in which a human body is captured; processing each of a plurality of first pixels of the first segmented image based on a reference value derived from all pixels of the input image; selecting a first reference image for the first human body part from a set of reference images; determining whether a partial region matching the first reference image exists based on a result of an operation between the first pixel of the first divided image processed by the reference value and a second pixel of the first reference image corresponding to the first pixel; determining a bone age class of the first human body part presented by the partial region based on the first reference image; and deriving a bone age of the human body based on the bone age rating.)

1. An electronic device, comprising:

a memory configured to store a reference image set including a plurality of reference images for a plurality of human body parts; and

a processor communicatively connected with the memory and configured to:

dividing an input image of a photographed human body into a plurality of divided images;

determining a first segmented image having a highest priority order for a first human body part of the plurality of human body parts from the plurality of segmented images;

processing each first pixel of the first divided image based on a reference value determined from all pixels of the input image;

selecting a first reference image for the first human body part from the set of reference images;

determining whether or not a partial region matching the first reference image exists within the first divided image processed by the reference value based on the calculation results for the first pixel of the first divided image processed by the reference value and a second pixel of the first reference image corresponding to the first pixel;

determining a bone age class of the first human body part based on the first reference image after determining that the partial region exists; and is

Determining a bone age of the human based on the bone age rating.

2. The electronic device of claim 1, wherein the processor is further configured to:

processing each first pixel of the first divided image by setting each pixel value of the first pixel of the first divided image smaller than the reference value to 0 and each pixel value of the first pixel of the first divided image equal to or larger than the reference value to a difference between each pixel value and the reference value.

3. The electronic device according to claim 2, wherein the reference value is an average value of all pixels of the input image.

4. The electronic device of claim 1, wherein the processor is further configured to:

multiplying a pixel value of each pixel of the partial region by a pixel value of each pixel of the first reference image corresponding to the each pixel of the partial region;

determining a matching score by summing the multiplied pixel values for the partial region; and is

Determining that the partial region matches the first reference image after determining that the matching score is equal to or greater than a preset value.

5. The electronic device of claim 1, wherein the processor is further configured to:

determining a bone age level of a second human body part from among the human body parts using a second segmentation image having a highest priority for the second human body part and a second reference image for the second human body part from the reference image set; and is

Determining a bone age of the human based on the bone age rating of the first human portion and the bone age rating of the second human portion.

6. The electronic device of claim 1, wherein the processor is further configured to:

after determining that the partial region does not exist, determining whether the partial region exists using a third divided image having a priority order after the first divided image for the first human body part and the first reference image.

7. The electronic device of claim 1, wherein the processor is further configured to:

adjusting the reference value after determining that the partial region does not exist;

processing each of the first pixels of the first segmented image based on the adjusted reference value; and is

Determining whether the partial region exists using the first divided image processed according to the adjusted reference value and the first reference image.

8. The electronic device of claim 1, wherein the memory is further configured to store a plurality of reference image sets according to race and gender, and

wherein the processor is further configured to:

a reference image set to be compared with the first divided image is determined from among the plurality of reference image sets based on race information and gender information input from a user.

9. The electronic device of claim 1, wherein the processor is further configured to:

the bone age rating of the first human body part was determined according to the TW3(Tannery-Whitehouse third edition) method.

10. A method, comprising:

dividing an input image of a photographed human body into a plurality of divided images;

determining a first segmented image having a highest priority order for a first human body part of a plurality of human body parts from the plurality of segmented images;

processing each first pixel of the first divided image based on a reference value determined from all pixels of the input image;

selecting a first reference image for a first human body part from a reference image set including a plurality of reference images for each of the human body parts;

determining whether or not a partial region matching the first reference image exists within the first divided image processed by the reference value based on the calculation results for the first pixel of the first divided image processed by the reference value and a second pixel of the first reference image corresponding to the first pixel;

determining a bone age class of the first human body part based on the first reference image after determining that the partial region exists; and

determining a bone age of the human based on the bone age rating.

11. The method of claim 10, wherein processing each of the first pixels of the first segmented image comprises:

processing each first pixel of the first divided image by setting each pixel value of the first pixel of the first divided image smaller than the reference value to 0 and each pixel value of the first pixel of the first divided image equal to or larger than the reference value to a difference between each pixel value and the reference value.

12. The method of claim 10, wherein determining whether the partial region matching the first reference image exists comprises:

multiplying a pixel value of each pixel of the partial region by a pixel value of each pixel of the first reference image corresponding to the each pixel of the partial region;

determining a matching score by summing the multiplied pixel values for the partial region; and is

Determining that the partial region matches the first reference image after determining that the matching score is equal to or greater than a preset value.

13. A non-transitory computer-readable recording medium storing a program to be executed on a computer, wherein the program comprises executable instructions that, when executed by a processor, cause the processor to perform:

dividing an input image of a photographed human body into a plurality of divided images;

determining a first segmented image having a highest priority order for a first human body part of a plurality of human body parts from the plurality of segmented images;

processing each first pixel of the first divided image based on a reference value determined from all pixels of the input image;

selecting a first reference image for a first human body part from a reference image set including a plurality of reference images for each of the human body parts;

determining whether or not a partial region matching the first reference image exists within the first divided image processed by the reference value based on the calculation results for the first pixel of the first divided image processed by the reference value and a second pixel of the first reference image corresponding to the first pixel;

determining a bone age class of the first human body part based on the first reference image after determining that the partial region exists; and

determining a bone age of the human based on the bone age rating.

14. The recording medium of claim 13, wherein processing each of the first pixels of the first segmented image comprises:

processing each first pixel of the first divided image by setting each pixel value of the first pixel of the first divided image smaller than the reference value to 0 and each pixel value of the first pixel of the first divided image equal to or larger than the reference value to a difference between each pixel value and the reference value.

15. The recording medium of claim 13, wherein determining whether the partial region matching the first reference image exists comprises:

multiplying a pixel value of each pixel of the partial region by a pixel value of each pixel of the first reference image corresponding to the each pixel of the partial region;

determining a matching score by summing the multiplied pixel values for the partial region; and

determining that the partial region matches the first reference image after determining that the matching score is equal to or greater than a preset value.

16. The recording medium of claim 13, wherein the program includes executable instructions that, when executed by the processor, cause the processor to further perform:

after determining that the partial region does not exist, determining whether the partial region exists using a third divided image having a priority order after the first divided image for the first human body part and the first reference image.

17. The recording medium of claim 13, wherein the program includes executable instructions that, when executed by the processor, cause the processor to further perform:

adjusting the reference value after determining that the partial region does not exist;

processing each of the first pixels of the first segmented image based on the adjusted reference value; and

determining whether the partial region exists using the first divided image processed according to the adjusted reference value and the first reference image.

Technical Field

The present disclosure relates to techniques for bone age assessment.

Background

The bone age of a patient may be estimated from medical images (e.g., X-ray images, etc.) of the patient's anatomy. By assessing the bone age of a patient and comparing it to the actual age of the patient, the growth potential of the corresponding body part can be determined. In addition, from the bone age of the patient, it can be determined whether each body part is normally grown according to the human development process.

To determine the bone age of a patient, the Greulich-Pyle (G & P) method or the Tanner-Whitehouse (TW) method may be used. The G & P method is a method of comparing a medical image of a patient with images representing respective ages to determine an age at which the degree of bone maturity is closest. The TW method is a method of determining the bone age of a patient by analyzing and ranking the bone shape and density of each human body part. However, both methods have a problem in that the image comparison job is manually performed, and thus the accuracy of image comparison is poor.

Disclosure of Invention

Technical problem

Embodiments of the present disclosure provide techniques for bone age assessment that address the above-mentioned issues.

Technical scheme

As an aspect of the present disclosure, an electronic device for bone age assessment may be presented. An electronic device according to an aspect of the present disclosure may include: a memory configured to store a reference image set including a plurality of reference images for a plurality of human body parts; and a processor communicatively connected with the memory and configured to: dividing an input image of a photographed human body into a plurality of divided images; determining a first segmented image having a highest priority order for a first human body part of the plurality of human body parts from the plurality of segmented images; processing each first pixel of the first divided image based on a reference value determined from all pixels of the input image; selecting a first reference image for the first human body part from the set of reference images; determining whether or not a partial region matching the first reference image exists within the first divided image processed by the reference value based on the calculation results for the first pixel of the first divided image processed by the reference value and a second pixel of the first reference image corresponding to the first pixel; determining a bone age class of the first human body part based on the first reference image after determining that the partial region exists; and determining a bone age of the human body based on the bone age rating.

In an embodiment, the processor may be further configured to: processing each first pixel of the first divided image by setting each pixel value of the first pixel of the first divided image smaller than the reference value to 0 and each pixel value of the first pixel of the first divided image equal to or larger than the reference value to a difference between each pixel value and the reference value.

In one embodiment, the reference value may be an average value of all pixels of the input image.

In an embodiment, the processor may be further configured to: multiplying a pixel value of each pixel of the partial region by a pixel value of each pixel of the first reference image corresponding to the each pixel of the partial region; determining a matching score by summing the multiplied pixel values for the partial region; and determining that the partial region matches the first reference image after determining that the matching score is equal to or greater than a preset value.

In an embodiment, the processor may be further configured to: determining a bone age level of a second human body part from among the human body parts using a second segmentation image having a highest priority for the second human body part and a second reference image for the second human body part from the reference image set; and determining the bone age of the person based on the bone age class of the first person part and the bone age class of the second person part.

In an embodiment, the processor may be further configured to: after determining that the partial region does not exist, determining whether the partial region exists using a third divided image having a priority order after the first divided image for the first human body part and the first reference image.

In an embodiment, the processor may be further configured to: adjusting the reference value after determining that the partial region does not exist; processing each of the first pixels of the first segmented image based on the adjusted reference value; and determining whether the partial region exists using the first divided image processed according to the adjusted reference value and the first reference image.

In an embodiment, the memory may be further configured to store a plurality of reference image sets according to a race and a gender, and the processor may be further configured to determine a reference image set to be compared with the first segmentation image from among the plurality of reference image sets based on race information and gender information input from a user.

In an embodiment, the processor may be further configured to determine the bone age rating of the first human body part according to a TW3(Tannery-Whitehouse third edition) method.

As another aspect of the present disclosure, a method for bone age assessment may be presented. A method according to another aspect of the present disclosure may include: dividing an input image of a photographed human body into a plurality of divided images; determining a first segmented image having a highest priority order for a first human body part of a plurality of human body parts from the plurality of segmented images; processing each first pixel of the first divided image based on a reference value determined from all pixels of the input image; selecting a first reference image for a first human body part from a reference image set including a plurality of reference images for each of the human body parts; determining whether or not a partial region matching the first reference image exists within the first divided image processed by the reference value based on the calculation results for the first pixel of the first divided image processed by the reference value and a second pixel of the first reference image corresponding to the first pixel; determining a bone age class of the first human body part based on the first reference image after determining that the partial region exists; and determining the bone age of the human body based on the bone age rating.

In an embodiment, processing each of the first pixels of the first segmented image may include: processing each first pixel of the first divided image by setting each pixel value of the first pixel of the first divided image smaller than the reference value to 0 and each pixel value of the first pixel of the first divided image equal to or larger than the reference value to a difference between each pixel value and the reference value.

In an embodiment, determining whether there is the partial region matching the first reference image may include: multiplying a pixel value of each pixel of the partial region by a pixel value of each pixel of the first reference image corresponding to the each pixel of the partial region; determining a matching score by summing the multiplied pixel values for the partial region; and determining that the partial region matches the first reference image after determining that the matching score is equal to or greater than a preset value.

As still another aspect of the present disclosure, a recording medium storing a program for bone age assessment may be proposed. The recording medium according to still another aspect of the present disclosure may be a non-transitory computer-readable recording medium storing a program to be executed on a computer. The program may include executable instructions that, when executed by a processor, cause the processor to perform: dividing an input image of a photographed human body into a plurality of divided images; determining a first segmented image having a highest priority order for a first human body part of a plurality of human body parts from the plurality of segmented images; processing each first pixel of the first divided image based on a reference value determined from all pixels of the input image; selecting a first reference image for a first human body part from a reference image set including a plurality of reference images for each of the human body parts; determining whether or not a partial region matching the first reference image exists within the first divided image processed by the reference value based on the calculation results for the first pixel of the first divided image processed by the reference value and a second pixel of the first reference image corresponding to the first pixel; determining a bone age class of the first human body part based on the first reference image after determining that the partial region exists; and deriving the bone age of the human body based on the bone age rating.

In an embodiment, processing each of the first pixels of the first segmented image may include: processing each first pixel of the first divided image by setting each pixel value of the first pixel of the first divided image smaller than the reference value to 0 and each pixel value of the first pixel of the first divided image equal to or larger than the reference value to a difference between each pixel value and the reference value.

In an embodiment, determining whether there is the partial region matching the first reference image may include: multiplying a pixel value of each pixel of the partial region by a pixel value of each pixel of the first reference image corresponding to the each pixel of the partial region; determining a matching score by summing the multiplied pixel values for the partial region; and determining that the partial region matches the first reference image after determining that the matching score is equal to or greater than a preset value.

In an embodiment, the program may include executable instructions that, when executed by the processor, cause the processor to further perform: after determining that the partial region does not exist, determining whether the partial region exists using a third divided image having a priority order after the first divided image for the first human body part and the first reference image.

In an embodiment, the program may include executable instructions that, when executed by the processor, cause the processor to further perform: adjusting the reference value after determining that the partial region does not exist; processing each of the first pixels of the first segmented image based on the adjusted reference value; and determining whether the partial region exists using the first divided image processed according to the adjusted reference value and the first reference image.

Effects of the invention

According to various embodiments of the present disclosure, the bone age of a patient can be estimated by automatically comparing an image of the patient's body with a reference image of a body part.

According to various embodiments of the present disclosure, image comparison and bone age assessment can be accurately performed by comparing shapes between an image of a human body and a reference image by pattern matching of pixels.

According to various embodiments of the present disclosure, it is possible to reduce the amount of calculation consumed for image comparison by dividing an image of a human body into regions to perform image comparison, or by setting a priority order to the regions.

Drawings

Fig. 1 illustrates the operation of an electronic device according to an embodiment of the present disclosure.

Fig. 2 illustrates a block diagram of an electronic device 200 according to various embodiments of the present disclosure.

FIG. 3 illustrates a process of processing pixels of a segmented image according to an embodiment of the disclosure.

Fig. 4 illustrates a process of finding a partial region matching a reference image within a segmented image according to an embodiment of the present disclosure.

Fig. 5 illustrates a process of determining a bone age of a human based on bone age ratings for a plurality of human parts according to an embodiment of the present disclosure.

Fig. 6 illustrates a process of selecting a segmented image to be compared with a next reference image according to a priority order according to an embodiment of the present disclosure.

Fig. 7 illustrates a process of adjusting a reference value when there is no matching partial region according to an embodiment of the present disclosure.

FIG. 8 illustrates a plurality of reference image sets according to an embodiment of the present disclosure.

FIG. 9 illustrates a reference image for a plurality of human body parts and a bone age rating for each human body part according to an embodiment of the disclosure.

Fig. 10 illustrates a bone age assessment method that may be performed by the electronic device 200 according to an embodiment of the present disclosure.

Detailed Description

The various embodiments described in the present specification are exemplified for the purpose of clearly explaining the technical idea of the present disclosure, and are not intended to limit the technical idea of the present disclosure to specific embodiments. The technical idea of the present disclosure includes various modifications, equivalents, alternatives of the embodiments described in the present specification, and embodiments selectively combined from all or a part of the embodiments. The scope of the technical idea of the present disclosure is not limited to the various embodiments presented below or the specific description thereof.

Unless otherwise specified, terms (including technical or scientific terms) used herein may have meanings that are commonly understood by one of ordinary skill in the art to which this disclosure belongs.

As used herein, expressions such as "comprising," "may include," "provided," "may be provided with," "have," "may have" or the like mean that there are subject features (e.g., functions, operations, components, etc.), and do not preclude the presence of other additional features. That is, these expressions should be understood as implying open terms including the possibilities of other embodiments.

Unless otherwise stated, the singular expressions may include a plurality, and the same applies to the singular expressions recited in the claims.

The terms "first," "second," and the like as used herein are used to distinguish one element from another, and are not intended to limit the order or importance of the related elements.

As used herein, expressions such as "A, B and C", "A, B or C", "A, B and/or C", "at least one of A, B and C", "at least one of A, B or C", "at least one of A, B and/or C", "at least one selected from A, B and C", "at least one selected from A, B or C" and "at least one selected from A, B and/or C" may mean the individual listed items or all possible combinations of the listed items. For example, the expression "at least one selected from a and B" may refer to both (1) at least one a, (2) at least one B, (3) at least one a and at least one B.

The term "component" as used in these embodiments means a software component, or a hardware component such as a Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC). However, "component" is not limited to hardware and software, and "component" may also be configured as an addressable storage medium or may be configured to run on one or more processors. For example, a "component" may include components such as software components, object-oriented software components, class components and task components, as well as processors, functions, attributes, programs, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.

The expression "based on" or "according to" as used herein is used to describe one or more factors that affect a decision, a judged action or operation described in a phrase or sentence containing the relevant expression, and the expression does not exclude additional factors that affect a decision, a judged action or operation.

As used herein, the expression that a certain component (e.g., a first component) is "connected" to another component (e.g., a second component) may mean that the certain component is connected or coupled not only directly to the other component but also via a new other component (e.g., a third component).

As used herein, the expression "configured to" may have meanings such as "set to", "have the ability of", "change to", "make", "enable", and the like, depending on the context. The expression is not limited to the meaning of "specifically designed for hardware". For example, a processor configured to perform certain operations may mean a general-purpose processor capable of performing certain operations by executing software.

Hereinafter, various embodiments of the present disclosure will be described with reference to the accompanying drawings. In the drawings and the description thereof, the same or substantially the same elements may be given the same reference numerals. In addition, in the following description of the various embodiments, repeated descriptions of the same or corresponding elements may be omitted. However, this does not mean that the elements are not included in these embodiments.

Fig. 1 illustrates the operation of an electronic device (not shown) according to an embodiment of the present disclosure. A bone age assessment device according to the present disclosure may be implemented by an electronic device according to various embodiments. The electronic device according to various embodiments of the present disclosure may determine the bone age by comparing an input image obtained by photographing a human body with a reference image for each human body part. The electronic devices to be described below may include one or more computers and/or servers. The computer and/or server may be communicatively connected, for example, by a network. Each computer and/or each server may include one or more processors and/or one or more memories (or storage devices).

Specifically, the electronic device may acquire an input image 110 obtained by photographing a human body. The input image 110 may be a medical image (e.g., an X-ray image) of a portion of a human body, and may be an image obtained, for example, by photographing a hand of a patient. The electronic device may divide the input image 110 into a plurality of segmented images. The input image 110 may be divided in various ways according to the intention of an implementer. In one embodiment, the electronic device may equally divide the input image 110 into 9 rectangular divided images.

The electronics can select the first segmented image 120 from the plurality of segmented images. The selected first divided image 120 may be a divided image having the highest priority order for a first human body part that is one of the human body parts. In the present disclosure, the priority order of the segmentation images for a specific human body part may mean a probability degree that the segmentation images include an image of the specific human body part. That is, the divided image 120 having the highest priority order for the specific human body part (e.g., the first human body part) may mean that the probability that the divided image 120 includes an image of the specific human body part is highest among the plurality of divided images. In the input image 110 obtained by photographing a human body (e.g., hand), which divided image of the input image includes a specific human body part (e.g., wrist joint) may be different according to the shape and size of the human body (e.g., hand) and the position of the human body at the time of imaging. However, statistically, the probability that the specific human body part (e.g., the wrist joint) is included in a specific segmented image 120 may be higher than the probability that it is included in other segmented images. Each segmented image may have a priority order for each body part based on the probability that each body part is included. In the illustrated embodiment, it can be said that the segmented image 120 has the highest priority for the first human body part.

The electronics can process each first pixel of the first segmented image 120 based on a reference value determined from all pixels of the input image 110. Each pixel of the input image 110 may have a pixel value. The reference value may be determined in a predetermined manner based on the pixel values of the pixels of the input image 110. The electronics can compare the pixel value of the first pixel of the first segmented image 120 to a reference value and can adjust the pixel value of the first pixel according to a predetermined criterion. A specific method of processing the pixel value of the first pixel of the first divided image 120 will be described later.

In one aspect, the electronic device can select a first reference image 150 for a first human body part from a set of reference images 140. The electronic device can store one or more reference image sets, and each reference image set can include one or more reference images.

In the present disclosure, the reference image may be an image showing a reference morphology of a human body part at a specific bone age. Each reference image may be associated with a particular body part and a particular bone age level for that body part. The reference image may be compared with the input image (or the segmented image) and used to determine the body part represented by a particular region in the input image and the determined bone age of the body part. For example, if a partial region corresponding to one reference image exists in the input image (or the divided image), the partial region may be a region corresponding to a human body part (for example, a wrist joint) presented by the reference image. Meanwhile, a human body part (e.g., a wrist joint) presented by the partial region may be determined to have a bone age (e.g., a bone age of 5 years) indicated by the reference image. In the present disclosure, the reference image set may be a set of reference images classified according to a specific race and/or gender. One reference image set may include reference images of a plurality of human body parts and a plurality of bone ages for respective races and/or sexes.

The electronics can compare the first segmented image 130, which is the first segmented image 120 processed by the reference value, with the selected first reference image 150. In the comparison process, the electronics can perform a pixel-by-pixel calculation between a first pixel of the first segmented image 130 and a second pixel of the first reference image 150 corresponding to the first pixel. Based on the calculation result, it can be determined whether or not the partial region 170 matching the first reference image 150 exists within the first divided image 130. The specific procedure of the pixel-by-pixel calculation will be described later.

If it is determined that the partial region 170 is present, the electronic device may determine a bone age rating of the first human body part presented by the partial region 170 based on information associated with the first reference image 150 used in the comparison process. That is, if there is a partial region 170 matching the first reference image 150, it can be confirmed that the partial region 170 is a region where the first human body part indicated by the first reference image 150 is present. Further, the bone age class of the first human body part may be determined as the bone age class corresponding to the first reference image 150.

The electronic device may determine a bone age of the person (e.g., hand) based on the bone age rating determined for the first body part. In an embodiment, the electronic device may determine the bone age of the human body (e.g., hand) by determining bone age ratings for a plurality of human body parts and a first human body part and combining the determined bone age ratings.

Fig. 2 is a block diagram of an electronic device 200 according to various embodiments of the present disclosure. In an embodiment, the electronic device 200 may include a processor 210, a memory 220, an input device 230, and/or an output device 240. In an embodiment, at least one of these components of the electronic device 200 may be omitted, or another component may be added to the electronic device 200. Additionally or alternatively, some components may be implemented in an integrated form or in a single entity or multiple entities. In particular, the input device 230 and/or the output device 240 may be omitted from the electronic device 200. At least some of the internal and external components of the electronic device 200 may be connected to each other through a bus, a general purpose input/output (GPIO), a Serial Peripheral Interface (SPI), a Mobile Industry Processor Interface (MIPI), etc. so as to exchange data and/or signals.

The processor 210 may drive software (e.g., a program) to control at least one component of the electronic device 200 connected with the processor 210. Further, the processor 210 may perform various operations related to the present disclosure, such as calculations, processing, data generation, processing, and the like. Further, the processor 210 may load data from the memory 220, or the like, or may store data in the memory 220.

The processor 210 may divide an input image in which a human body is photographed into a plurality of divided images. The processor 210 may determine (select) a first segmented image with highest priority for the first human body part from the plurality of segmented images. The processor 210 may process each of the determined plurality of first pixels of the first divided image based on the aforementioned reference value. Further, processor 210 may select a first reference image for a first human body part from a set of reference images.

The processor 210 may compare the first divided image processed by the reference value with the first reference image. Specifically, the processor 210 may calculate each of a plurality of first pixels of the first divided image and each of a plurality of second pixels of the first reference image corresponding to each of the first pixels. The processor 210 may determine whether or not a partial region matching the first reference image exists within the first divided image based on the calculation result.

If it is determined that the partial region exists, the processor 210 may determine that the partial region is a region presenting a first human body part and may determine a bone age rating associated with the first reference image as the bone age rating of the first human body part. The processor 210 may determine the bone age of the human body (e.g., hand) based on the determined bone age rating. In one embodiment, processor 210 may use various methods of determining a bone age rating of a first human body part based on a first reference image. For example, the TW3(Tanner-Whitehouse third edition) method may be used in determining bone age ratings. Data (e.g., a bone shape atlas, etc.) needed to perform the method of determining the respective bone age level may be stored in memory 220.

The memory 220 may store various types of data. The data stored in the memory 220 may be data including data acquired, processed, or used by at least one component of the electronic device 200, and may include software (e.g., a program). The memory 220 may include volatile memory and/or non-volatile memory. The memory 220 may store at least one or more reference image sets.

In the present disclosure, the program is software stored in the memory 220, and may include an operating system for controlling resources of the electronic device 200, applications, and/or middleware for providing various functions to the applications to enable the applications to utilize the resources of the electronic device. An application may be a concept that includes an application running on a mobile device.

In an embodiment, the electronic device 200 may further include an input device 230. The input device may be a device that receives data to be transmitted from outside the electronic device 200 to at least one component of the electronic device 200. For example, the input device may include a mouse, a keyboard, a touch pad, and the like.

In an embodiment, the electronic device 200 may further include an output device 240. The output device may be a device that provides various data such as the inspection result of the electronic device 200, the operation state thereof, and the like to the user in a visual form. For example, the output device may include a display, a projector, a hologram, or the like.

In an embodiment, the electronic device 200 may further include a communication interface (not shown). The communication interface may perform wireless or wired communication between the electronic device 200 and a server or between the electronic device 200 and other external electronic devices. For example, the communication interface may perform wireless communication according to a method such as LTE (long term evolution), LTE-a (LTE advance), CDMA (code division multiple access), WCDMA (wideband CDMA), WiBro (wireless broadband), WiFi (wireless fidelity), Bluetooth (Bluetooth), NFC (near field communication), GPS (global positioning system), or GNSS (global navigation satellite system). For example, the communication interface may perform wired communication according to a method such as USB (universal serial bus), HDMI (high definition multimedia interface), RS-232 (recommended standard 232), or POTS (plain old telephone service). In one embodiment, the processor 210 may obtain information from a server through a control communication interface. The information obtained from the server may be stored in the memory 220. In one embodiment, the information obtained from the server may include at least one reference image set.

In an embodiment, the electronic device 200 may be various types of devices. For example, the electronic device 200 may be a portable communication device, a computer device, a portable multimedia device, a wearable device, or a device obtained by combining the above devices. The electronic device 200 of the present disclosure is not limited to the aforementioned devices.

Various embodiments of the electronic device 200 according to the present disclosure may be combined with each other. The respective embodiments may be combined according to the number of cases. Embodiments of the electronic device 200 resulting from such combinations also fall within the scope of the present disclosure. In addition, the aforementioned internal/external components of the electronic device 200 according to the present disclosure may be added, changed, substituted, or deleted according to embodiments. In addition, the aforementioned internal/external components of the electronic device 200 may be implemented as hardware components.

FIG. 3 illustrates a process of processing pixels of a segmented image according to an embodiment of the disclosure. As described above, the processor 210 may process each of the plurality of first pixels of the first divided image based on the reference value determined from all the pixels of the input image. In the present disclosure, the pixels of the segmented image may be processed in various ways prior to the comparison process with the reference image.

In an embodiment, the processor 210 may adjust each pixel value of the plurality of first pixels of the first segmented image 120 based on the reference value. Specifically, the processor 210 may set a pixel value of each first pixel of the first divided image 120, which is smaller than the reference value, to 0. Further, the processor 210 may set a pixel value of each first pixel of the first divided image 120, which is equal to or greater than the reference value, as a difference value between the reference value and the corresponding pixel value.

Generally, an input image (or a segmentation image) such as an X-ray image or the like is photographed as black and white. On the input image, soft tissue such as skin, flesh, etc. may appear in gray, while on the input image, hard tissue such as bone, etc. appears in white. As described above, if the pixel value is adjusted according to the reference value, the soft tissue portion rendered in gray becomes black because its pixel value becomes 0. Therefore, the shape of the soft tissue portion may disappear from the input image. On the other hand, the hard tissue appearing in white retains its shape even after the above-described treatment. As a result, it is possible to reduce an error due to soft tissue in comparison with the reference image to be performed later. This enables a clear comparison between the actual bone shape and the reference image to be performed. As shown, the first segmented image 120 may be processed as the first segmented image 130 according to the above-described process. It can be said that the first segmented image 130 after processing does not reveal soft tissue compared to the first segmented image 120 before processing.

In an embodiment, the reference value may be an average value of pixel values of all pixels of the input image. In an embodiment, the reference value may be a value determined by the processor 210, or may be a value predetermined, stored in the memory 220, and loaded by the processor 210 as needed. In an embodiment, the processor 210 may set a pixel value of each first pixel of the first divided image 120, which is equal to or greater than the reference value, to a maximum value (e.g., 100). In an embodiment, the processor 210 may not adjust the pixel value of each first pixel of the first divided image 120, which is equal to or greater than the reference value, and may leave the original pixel value unchanged.

Fig. 4 illustrates a process of finding a partial region matching a reference image within a segmented image according to an embodiment of the present disclosure. As described above, the processor 210 may compare the first divided image processed by the reference value with the first reference image. The processor 210 may calculate each of a plurality of first pixels of the first divided image and each of a plurality of second pixels of the first reference image corresponding to each of the first pixels. Based on the calculation result, the processor 210 may determine whether there is a partial region matching the first reference image within the first divided image.

Specifically, the processor 210 may compare the first divided image 410 processed according to the reference value with the first reference image 420. The first reference image 420 may be an image showing a shape of a first human body part at a specific bone age, which is one of the human body parts. In the comparison process, the processor 210 may scan the first segmented image 410 with the first reference image 420 to determine whether there is a partial region having a shape matching the first reference image 420 within the first segmented image 410.

The processor 210 may determine whether there is a partial region 430 within the first segmented image 410 that matches the first reference image 420. The determination of whether or not a partial region matches the first reference image 420 may be performed based on a calculation result obtained by performing pixel-by-pixel calculation between the partial region and the first reference image 420.

Such pixel-by-pixel calculations may be performed in accordance with various embodiments. In an embodiment, the processor 210 may multiply each pixel value of each pixel of a partial region by each pixel value of each corresponding pixel of the first reference image, and may determine whether the partial region matches the first reference image based on a matching score determined by summing the multiplication results for each pixel value. Specifically, the processor 210 may multiply the pixel value of each pixel of a partial region (region indicated by a rectangle in fig. 4) of the first divided image 410 processed by the reference value and the pixel value of each pixel of the first reference image 420 corresponding to the pixel value of each pixel of the partial region. In this regard, the resolutions (i.e., the numbers of horizontal and vertical pixels) of the partial region and the first reference image 420 may be the same as each other. The corresponding pixel may mean a pixel located at the same position in the partial region and the first reference image 420. The processor 210 may then determine a match score by adding all of the multiplication results for each pixel. When the determined matching score is equal to or greater than a preset value, the processor 210 may determine that the partial region is a region matching the first reference image 420 (i.e., the partial region 430).

For example, the pixel values of the partial region of the first divided image processed by the reference value may be presented as illustrated in the pixel value distribution 412. Further, the pixel values of the first reference image may be presented as illustrated by the illustrated pixel value distribution 422. The processor 210 may multiply the pixel values of the corresponding pixels, add the multiplied pixel values for each corresponding pixel, and determine a matching score. That is, in this case, the matching score may be determined as (50 × 30) + (20 × 30) + (50 × 30) ═ 6600. Values that do not affect the matching score due to multiplication with a pixel value of 0 are excluded from the equation. If the preset reference value is, for example, 5000, the corresponding partial region may be determined as the partial region matching the first reference image.

In one embodiment, a predetermined value to be compared to the matching score may be stored in the memory 220. In an embodiment, the processor 210 may not compare the determined matching score with a preset value, but may determine a partial region having the highest matching score in the first divided image 410 as the partial region 430 matching the first reference image 420. In one embodiment, to determine the partial region matching the first reference image 420, a pattern matching algorithm different from the pattern matching algorithm described above may be used.

Fig. 5 illustrates a process of determining a bone age of a human based on bone age ratings for a plurality of human parts according to an embodiment of the present disclosure. In an embodiment, the electronic device 200 may determine a bone age grade for each of a plurality of body parts (e.g., thumb joints, wrist joints, etc.) of a body (e.g., hand) in the same manner as described above, and may determine the bone age of the entire body (e.g., hand) in consideration of the bone age grades for the respective body parts.

The human body that is the subject of bone age assessment may include multiple human body sites. The plurality of body parts may be the main parts of the body that can have an influence on the final determination of the age of the bones of the body. For example, in the case of the hand, about 13 major body parts may be used for image comparison to determine bone age. The aforementioned reference image set may include reference images for a plurality of human body parts corresponding to respective bone ages.

As described in the method of determining a bone age grade for a first human body part according to the above process, the processor 210 may determine a bone age grade for another human body part (e.g., a second human body part). The processor 210 may determine a second segmented image having a highest priority order for a second human body part among the plurality of human body parts. The processor 210 may process pixels of the second segmented image based on the reference values and may compare the processed second segmented image with a second reference image for a second human body part. The comparison process may be performed in the same manner as described above. Accordingly, the processor 210 may determine a bone age rating of the second human body part. The processor 210 may determine the bone age of the person by considering the bone age class determined for the first person part, the bone age class determined for the second person part and/or the bone age class determined for other person parts.

For example, the processor 210 may first determine a bone age rating for the illustrated human body parts 510, 520, 530, etc. The body part 510, the body part 520, and the body part 530 may be determined to have bone age ratings B, D and E, respectively. Bone age ratings for other body parts can be determined in the same manner. The processor 210 may determine an overall score for the respective human based on the respective bone age level. In the illustrated embodiment, the overall score is determined to be 259. Therefore, the bone age of the human body can be determined to be 7.42. The process of determining bone age from the overall score may be performed based on information (e.g., a look-up table) pre-stored in memory 220.

In an embodiment, the processor 210 may determine the bone age based only on the bone age levels for some human body parts selected according to the predetermined criteria, rather than the bone age levels for all of the plurality of human body parts. In one embodiment, the processor 210 may determine bone age by weighting the bone age levels of some body parts according to predetermined criteria. This is because each body part may have a different degree of influence on the determination of the overall bone age. In an embodiment, when the bone age rating of a particular human body part exceeds the bone age ratings of other parts by a predetermined amount or more, the processor 210 may determine that the bone age rating determined for the particular human body part is erroneous, and may exclude the bone age rating of the particular human body part when determining the overall bone age.

Fig. 6 illustrates a process of selecting a divided image to be compared with a next reference image according to a priority order according to an embodiment of the present disclosure. As described above, each of the divided images has a priority order of performing image comparison for a human body part according to the probability of including the human body part. For example, in an input image 610 for a human body (e.g., a hand), a probability that a human body part (e.g., a wrist joint) is included in a particular segmented image 620 of the input image 610 may be high. Although there may be an error depending on the shape and size of a human body (e.g., a hand) and the position of the human body at the time of image capturing, statistically, the probability that a human body part (e.g., a wrist joint) is included in a certain segmented image 620 may be higher than the probability that a human body part is included in other segmented images. That is, the divided images may have a priority order of performing image comparison for respective human body parts according to a probability that a human body part is included in each divided image.

In an embodiment, if the electronic apparatus 200 does not find a partial region matching the first reference image from the first divided image having the highest priority order for the first human body part, the electronic apparatus 200 may continue to find a matching partial region in the third divided image having the next priority order (the second highest priority order) for the first human body part. Specifically, the processor 210 may determine that there is no partial region matching the first reference image within the first divided image 620 processed by the reference value. In this case, if it is determined that the partial region does not exist, the processor 210 may determine a third segmentation image 630 having a priority order after the first segmentation image for the first human body part. As described above, the processor 210 may process the pixel values of the third divided image 630 based on the reference value. The processor 210 may compare the processed third segmented image 630 with the first reference image to determine whether there is a partial region within the third segmented image 630 that matches the first reference image. If a corresponding partial region exists within the third segmented image 630, it may be determined that the corresponding partial region represents a first human body part, and it may be further determined that the first human body part has a bone age rating associated with the first reference image.

In an embodiment, if there is no partial region matching the first reference image even in the segmented image having the next order of priority (e.g., the third segmented image), the processor 210 may continue to search for a matching partial region in the segmented image having the order of priority after the third segmented image for the first human body part. Thereafter, the processor 210 may sequentially search for the divided images according to the order of priority for the first human body part.

In an embodiment, the processor 210 may not perform the operation of comparing with the first reference image in the divided image having the priority order for the human body part lower than the predetermined priority order. This is because, for example, if a shape matching the first reference image is found at a position where the probability that a partial region statistically matching the first human body part exists is low, the shape may indicate a human body part different from the first human body part or may be an error arbitrarily occurring in the input image.

Fig. 7 illustrates a process of adjusting a reference value when there is no matching partial region according to an embodiment of the present disclosure. In an embodiment, if it is determined that there is no partial region, the electronic device 200 may adjust the reference value described above, may reprocess the pixel value of the first divided image, and may newly compare the first divided image with the first reference image. By processing the pixel values with the adjusted reference values, the black and white contrast of the first segmented image may be even clearer in some embodiments. Therefore, it is possible to further reduce errors in the matching operation with the first reference image.

Specifically, if it is determined that there is no partial region matching the first reference image in the first divided image processed by the reference value, the processor 210 may adjust the reference value for processing the first divided image. As described above, the reference value is a value determined based on all pixels of the input image, and may be an average value of all pixels of the input image in an embodiment. During the adjustment process, the processor 210 may use a value obtained by applying a predetermined ratio α to the previously used reference value as a new reference value (730). That is, the new reference value may be a value obtained by multiplying the existing reference value (e.g., 50, 55, etc.) by a predetermined ratio (e.g., 0.75, 1.25, etc.).

The processor 210 may process the first divided image 120 by using the new reference value (the adjusted reference value). Processing the first segmented image according to the new reference value may follow an embodiment wherein the first segmented image is processed according to the aforementioned reference value. The processor 210 may search for a partial region matching the first reference image in the first divided image 720 processed according to the adjusted reference value, and may determine whether a corresponding partial region exists. If a matching partial region is found in the first segmented image 720, the bone age class of the corresponding first human body part can be determined using the first reference image.

In an embodiment, various methods may be used to adjust the reference value. In an embodiment, the predetermined ratio for adjusting the reference value may be greater than or less than 1. In an embodiment, instead of multiplying the existing reference value by the predetermined ratio, the reference value may be determined from the pixel value of the input image in a different manner from the existing reference value and used as a new reference value. In an embodiment, the pre-processed first segmented image 120 may not be processed using the adjusted reference value. Instead, the pre-processed first segmented image 120 may be processed using the existing reference value, and then the processed first segmented image 120 may be further processed using the adjusted reference value.

FIG. 8 illustrates a plurality of reference image sets according to an embodiment of the present disclosure. The memory 220 may store a plurality of reference image sets. As described above, each reference image set may be a set of reference images classified according to a specific race and/or gender. A reference image set may include reference images for a plurality of body parts and a plurality of bone ages for respective races and/or sexes.

A reference image set may include reference images for each of a plurality of human body parts. For example, a set of reference images may include reference image 810 for a first body part, reference image 820 for a second body part, and reference image 830 for a third body part. The illustrated reference image may be illustrative, and the first, second, and third human body parts are not limited to the human body parts indicated by the illustrated reference image.

Further, within a set of reference images, reference image 810 for a body part (e.g., a first body part) may include reference images 812, 814, 816, 818, etc. for the bone age of the respective body part. For example, a set of reference images may include a reference image 812 corresponding to a bone age of 5 years old of the first human body part, a reference image 814 corresponding to a bone age of 6 years old of the first human body part, a reference image 816 corresponding to a bone age of 7 years old of the first human body part, a reference image 818 corresponding to a bone age of 8 years old of the first human body part, and so on.

The memory 220 may include a plurality of such reference image sets 142, 144, 146. As in the reference image set described above, each reference image set may include a reference image for each human body part and a reference image for each bone age of each human body part. Each reference image set may include reference images that exhibit a bone shape of a human body for a certain race and/or a sex. For example, one reference image set 142 may be a set of reference images for each body part of a black woman and each bone age for each body part of a black woman. Further, the other reference image sets 144 and 146 may be sets of reference images for each body part of japanese-earman and chinese-nationality female and each bone age of each body part of japanese-earman and chinese-nationality female, respectively.

In one embodiment, the input device 230 may receive human race information and/or sex information of a human body as an inspection target from a user. The processor 210 may determine a reference image set from among the reference image sets stored in the memory 220 based on the race information and/or gender information received from the user. The determined reference image set is a reference image set including reference images according to the received ethnicity information and/or gender information, and may include, for example, reference images to be compared with the first segmented images.

Fig. 9 illustrates a reference image for a plurality of human body parts and bone age levels for each human body part according to an embodiment of the present disclosure. As described above, a human body (e.g., a hand) may include major body parts (910) that can affect a bone age assessment of the human body. The illustrated body 910 may have 13 major body parts that will be the subject of image comparison for determining bone age. The selection and number of human body parts to be the subject of image comparison may vary in some embodiments and are not limited to the illustrated embodiments.

As described above, a reference image set may include reference images for bone ages of a plurality of human body parts. For example, a reference image set may include reference images (920) for the bone age of a body part (r) in a human body. The reference image 920 may present shapes for respective levels (e.g., B to E) of the corresponding human body part according to a bone growth process of the corresponding human body part. If a matching partial region is found by comparing the reference image having the C level with the input image (or the divided image), it can be determined that the corresponding partial region represents the human body part (r) and has a bone age level corresponding to the C level.

Fig. 10 illustrates a bone age assessment method that may be performed by the electronic device 200, in accordance with an embodiment of the present disclosure. Although the steps of a method or algorithm according to the present disclosure have been described in the illustrated flow chart in sequential order, the steps may be performed in any combination order capable of being performed by the present disclosure, in addition to being performed sequentially. The description according to the flowchart does not exclude changes or modifications to the method or algorithm and does not imply that any step is required or preferred. In an embodiment, at least some of the steps may be performed in parallel, repeatedly, or heuristically. In an embodiment, at least some of the steps may be omitted, or other steps may be added.

The electronic device 200 according to the present disclosure may perform a bone age assessment method according to various embodiments of the present disclosure. A bone age assessment method according to an embodiment of the present disclosure may include: dividing an input image into a plurality of divided images (S1010); determining a first segmented image from the plurality of segmented images (S1020); processing each pixel of the first divided image based on the reference value (S1030); selecting a first reference image for a first human body part of a human body from a set of reference images (S1040); determining whether or not a partial region matching the first reference image exists within the first divided image based on the calculation results for each pixel of the first divided image and each pixel of the first reference image (S1050); determining a bone age class of the first human body part after determining that the partial region exists (S1060); and/or determining the bone age of the human body based on the bone age grade (S1070).

In S1010, the processor 210 of the electronic device 200 may divide an input image for a human body into a plurality of divided images. In S1020, the processor 210 may determine a first divided image having a highest priority order for a first human body part among the plurality of human body parts from the divided images. In S1030, the processor 210 may process each first pixel of the first divided image based on a reference value determined from all pixels of the input image. In S1040, the processor 210 may select a first reference image for a first human body part from a reference image set including a plurality of reference images for each of a plurality of human body parts. In S1050, the processor 210 may calculate each of first pixels of the first divided image processed by the reference value and each of second pixels of the first reference image corresponding to the first pixels. Based on the calculation result of each pixel, the processor 210 may determine whether or not a partial region matching the first reference image exists within the first divided image processed by the reference value. In S1060, after determining that the corresponding partial region exists, the processor 210 may determine a bone age level of the first human body part represented by the partial region based on the first reference image. In S1070, the processor 210 may determine the bone age of the human body based on the determined bone age grade.

In an embodiment, processing (S1030) each first pixel of the first divided image may include: each first pixel of the first divided image is processed by setting a pixel value of each first pixel of the first divided image smaller than a reference value to 0 and setting a pixel value of each first pixel of the first divided image equal to or larger than the reference value to a difference between the pixel value and the reference value. In an embodiment, the reference value may be an average value of all pixels of the input image.

In an embodiment, determining whether there is a partial region matching the first reference image (S1050) may include: the processor 210 multiplies pixel values of respective pixels of a partial region of the first divided image processed according to the reference value and pixel values of respective pixels of the first reference image corresponding to the respective pixels of the partial region, determines a matching score by summing the multiplied pixel values for the partial region, and/or determines that the partial region is matched with the first reference image after determining that the matching score is equal to or greater than a preset value.

In one embodiment, the bone age assessment method may further comprise: the processor 210 determines a bone age level of a second human body part from the plurality of human body parts using a second segmentation image having a highest priority for the second human body part and a second reference image for the second human body part from the set of reference images; and/or determining a bone age of the person based on the bone age rating of the first person part and the bone age rating of the second person part.

In one embodiment, the bone age assessment method may further comprise: after determining that there is no partial region, the processor 210 determines whether there is a partial region using the third divided image having a priority order after the first divided image for the first human body part and the first reference image.

In one embodiment, the bone age assessment method may further comprise: after determining that there is no partial region, the processor 210 adjusts the reference value; processing each first pixel of the first segmented image based on the adjusted reference value; and/or determining whether a partial region exists using the first divided image processed according to the adjusted reference value and the first reference image.

In one embodiment, the bone age assessment method may further comprise: the processor 210 determines a reference image set to be compared with the first divided image from among the plurality of reference image sets based on the race information and/or gender information input from the user. In one embodiment, the bone age assessment method may further comprise: the input device 230 receives race information and/or gender information for a human body as a bone age estimation target from a user. In one embodiment, the memory 220 may store a plurality of reference image sets according to race and/or gender.

Various embodiments of the present disclosure may be implemented as software recorded on a machine-readable storage medium. The software may be software for implementing the various embodiments of the present disclosure described above. Software may be inferred from the various embodiments of the disclosure by programmers skilled in the art to which the disclosure pertains. For example, the software may be instructions (e.g., code or code segments) or programs that can be read by the device. The device is a device capable of operating according to an instruction called from a recording medium, and may be, for example, a computer. In an embodiment, the apparatus may be an electronic device 200 according to an embodiment of the present disclosure. In an embodiment, a processor of the device may execute the called instructions, enabling components of the device to perform functions corresponding to the instructions. In an embodiment, the processor may be the processor 210 according to an embodiment of the present disclosure. The recording medium may refer to any type of recording medium readable by a device in which data is stored. The recording medium may include, for example, ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like. In one embodiment, the recording medium may be the memory 220. In an embodiment, the recording medium may be implemented in a distributed form in computer systems connected through a network. The software may be distributed, stored and executed in a computer system or the like. The recording medium may be a non-transitory recording medium. A non-transitory recording medium refers to a medium that actually exists regardless of whether data is stored semi-permanently or temporarily, and does not include a signal that propagates in a temporary manner.

Although the technical idea of the present disclosure has been illustrated by examples described in some embodiments and illustrated in the drawings, it should be noted that various substitutions, modifications and changes can be made without departing from the scope of the present disclosure that can be understood by those of ordinary skill in the art to which the present disclosure pertains. Further, it is noted that such substitutions, modifications and changes are intended to fall within the scope of the appended claims.