阅读说明：本技术 一种结节纵横比提取装置 (Nodule aspect ratio extraction element ) 是由 陈奇富 于 2021-08-10 设计创作，主要内容包括：本发明涉及一种结节纵横比提取装置,包括：图像获取模块：用于获取带有结节的超声图像；感兴趣结节图像提取模块：用于通过选取若干感兴趣坐标点的方式对所述超声图像的结节边界进行截取,得到感兴趣结节图像；多边形结节获取模块：用于将所述感兴趣结节图像中相邻的感兴趣坐标点进行连线,得到多边形结节；结节高度和宽度计算模块：用于计算所述多边形结节的最大高度和最大宽度；结节纵横比计算模块：用于根据所述多边形结节的最大高度和最大宽度计算结节的纵横比。本发明能够对结节进行量化判断,有效避免由主观判断结节纵横比所引起的失误。(The invention relates to a nodule aspect ratio extraction device, comprising: an image acquisition module: for acquiring an ultrasound image with a nodule; the interesting nodule image extraction module: the node boundary of the ultrasonic image is intercepted in a mode of selecting a plurality of interested coordinate points, so that an interested node image is obtained; a polygonal nodule obtaining module: the system is used for connecting adjacent interested coordinate points in the interested nodule image to obtain a polygonal nodule; nodule height and width calculation module: for calculating the maximum height and maximum width of the polygonal nodule; a nodule aspect ratio calculation module: for calculating the aspect ratio of the polygon nodules from their maximum height and maximum width. The method can quantitatively judge the nodule, and effectively avoids errors caused by subjective judgment of the aspect ratio of the nodule.)

1. A nodule aspect ratio extraction apparatus comprising:

an image acquisition module: for acquiring an ultrasound image with a nodule;

the interesting nodule image extraction module: the node boundary of the ultrasonic image is intercepted in a mode of selecting a plurality of interested coordinate points, so that an interested node image is obtained;

a polygonal nodule obtaining module: the system is used for connecting adjacent interested coordinate points in the interested nodule image to obtain a polygonal nodule;

nodule height and width calculation module: for calculating the maximum height and maximum width of the polygonal nodule;

a nodule aspect ratio calculation module: for calculating the aspect ratio of the polygon nodules from their maximum height and maximum width.

2. The nodule aspect ratio extraction apparatus of claim 1, wherein the nodule height and width calculation module calculates the maximum height of the polygonal nodule by the formula:wherein L is_H(x) Max f (x) -min f (x); x is the abscissa of any vertical line of the polygonal nodule in the vertical direction; f (x) represents the value of the ordinate at which the perpendicular line with x as the abscissa intersects the polygonal nodule, and definesf:N→NⁿAnd W is the polygon nodule width.

3. The nodule aspect ratio extraction apparatus of claim 1, wherein the nodule height and width calculation module calculates the maximum width of the polygonal nodule by the formula:wherein L is_W(y)＝max f^-1(y)-min f^-1(y); y is the ordinate of an arbitrary horizontal line in the horizontal direction of the nodule image of interest, f^-1(y) represents the value of the abscissa at the intersection of the horizontal line with y as the ordinate and the polygonal nodule, and f is defined^-1:N→NⁿAnd H is the polygon nodule height.

4. The nodule aspect ratio extraction apparatus of claim 1, wherein the nodule aspect ratio calculation module calculates the aspect ratio of a nodule from the maximum height and the maximum width of the polygonal nodule, further comprising: when the nodule is a thyroid nodule, the maximum height of the polygonal nodule isAnd maximum widthCalculating the aspect ratio of the nodule to satisfyThe thyroid nodule is taller than wider; if the maximum height of the polygonal noduleAnd maximum widthCalculating the aspect ratio of the nodule to satisfyThe thyroid nodule width is greater than the height, where t is a predetermined constant.

5. The nodule aspect ratio extraction apparatus of claim 1, wherein the nodule aspect ratio calculation module calculates the aspect ratio of a nodule from the maximum height and the maximum width of the polygonal nodule, further comprising: when the nodule is a mammary gland nodule, the maximum height of the polygonal noduleAnd maximum widthCalculating the aspect ratio of the nodule to satisfyThe direction of breast nodule growth is not parallel to the skin; if the maximum height of the polygonal noduleAnd maximum widthCalculating the aspect ratio of the nodule to satisfyThe growth direction of the breast nodules is parallel to the skin, where t is a preset constant.

Technical Field

The invention relates to the technical field of auxiliary medical diagnosis, in particular to a nodule aspect ratio extraction device.

Background

Nowadays, with the increasing demand for rapid and accurate diagnosis and the shortage of clinical staff, machine learning methods have been increasingly applied to assist routine clinical diagnosis and show good effects. Analysis of nodules in pathological parts (such as thyroid and breast) has a crucial influence on the diagnosis result, so that quantitative analysis for characterizing nodules in pathological parts is clinically needed, rather than only staying at the stage of subjective analysis of thyroid cancer or breast cancer by doctors at present.

For example, thyroid cancer is one of the most common cancers in women worldwide, and women have three times the incidence rate of men. In 2018, thyroid cancer was one of every 20 confirmed cases of female cancer. Ultrasound imaging is a non-invasive, non-radiative, low-cost tumor diagnosis technique, however, due to the low quality of ultrasound images, identifying thyroid nodules and detecting tumor features from ultrasound images is a challenging task.

In general, the growth and development of a malignant tumor can be reflected by its shape, appearance, texture, composition, and many other factors. As an effective tool, grayscale Ultrasound (US) images can visualize these factors, helping physicians to better observe and understand the appearance of pathological sites. However, in current clinical practice, the reading of ultrasound image features is highly dependent on the subjective or semi-subjective analysis of the images by the sonographer, which limits the widespread use of ultrasound. Therefore, automated and accurate quantitative analysis of nodules is crucial for accurate diagnosis of cancer.

Thyroid imaging reporting and data system (TI-RADS) and breast imaging reporting and data system (BI-RADS) are guidelines for scientific measurement and reporting of thyroid and breast nodules. There is currently no study of quantitative characterization of TI-RADS or BI-RADS to improve the diagnostic performance of thyroid or breast cancer classification.

Disclosure of Invention

The technical problem to be solved by the invention is to provide a nodule aspect ratio extraction device, which can quantitatively judge nodules and effectively avoid errors caused by subjective judgment of nodule aspect ratios.

The technical scheme adopted by the invention for solving the technical problems is as follows: there is provided a nodule aspect ratio extraction apparatus comprising:

an image acquisition module: for acquiring an ultrasound image with a nodule;

the interesting nodule image extraction module: the node boundary of the ultrasonic image is intercepted in a mode of selecting a plurality of interested coordinate points, so that an interested node image is obtained;

a polygonal nodule obtaining module: the system is used for connecting adjacent interested coordinate points in the interested nodule image to obtain a polygonal nodule;

nodule height and width calculation module: for calculating the maximum height and maximum width of the polygonal nodule;

a nodule aspect ratio calculation module: for calculating the aspect ratio of the polygon nodules from their maximum height and maximum width.

The maximum height of the polygonal nodules is calculated in the nodule height and width calculation module, and the formula is as follows:wherein L is_H(x) Maxf (x) -minf (x); x is the abscissa of any vertical line of the polygonal nodule in the vertical direction; f (x) represents the value of the ordinate at the intersection of the polygon nodule and the perpendicular line with x as the abscissa, and defines f: N → NⁿAnd W is the polygon nodule width.

The maximum width of the polygonal nodule is calculated in the nodule height and width calculation module, and the formula is as follows:wherein L is_W(y)＝maxf^-1(y)-minf^-1(y); y is the ordinate of an arbitrary horizontal line in the horizontal direction of the nodule image of interest, f^-1(y) represents the value of the abscissa at the intersection of the horizontal line with y as the ordinate and the polygonal nodule, and f is defined^-1:N→NⁿAnd H is the polygon nodule height.

The nodule aspect ratio calculating module calculates the aspect ratio of the nodule according to the maximum height and the maximum width of the polygonal nodule, and further comprises: when the nodule is a thyroid nodule, the maximum height of the polygonal nodule isAnd maximum widthCalculating the aspect ratio of the nodule to satisfyThe thyroid nodule is taller than wider; if there are moreMaximum height of the edge-shaped nodulesAnd maximum widthCalculating the aspect ratio of the nodule to satisfyThe thyroid nodule width is greater than the height, where t is a predetermined constant.

The nodule aspect ratio calculating module calculates the aspect ratio of the nodule according to the maximum height and the maximum width of the polygonal nodule, and further comprises: when the nodule is a mammary gland nodule, the maximum height of the polygonal noduleAnd maximum widthCalculating the aspect ratio of the nodule to satisfyThe direction of breast nodule growth is not parallel to the skin; if the maximum height of the polygonal noduleAnd maximum widthCalculating the aspect ratio of the nodule to satisfyThe growth direction of the breast nodules is parallel to the skin, where t is a preset constant.

Advantageous effects

Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects: the method can quantitatively judge the nodule, effectively avoids errors caused by subjective judgment of the aspect ratio of the nodule, and improves the accuracy of good and malignant judgment of the nodule by taking the value of the aspect ratio of the nodule as a reference; the invention adopts different aspect ratio thresholds for nodules at different pathological parts, so that the invention is more reasonable and more standardized; the method can calculate the maximum values of the nodules in height and width, so that the accuracy of judging the benign and malignant properties of the nodules at different pathological positions can be effectively improved; the method can effectively help doctors to judge the quality of the nodules, reduces the actual workload of the doctors, and is suitable for practical popularization and use.

Drawings

FIG. 1 is a flow chart of an embodiment of the present invention;

FIG. 2 is a schematic diagram of coordinate points of interest of a thyroid nodule in an embodiment of the present invention;

FIG. 3 is a schematic diagram of a polygon formed by connecting lines of coordinate points of interest of a thyroid nodule according to an embodiment of the present invention;

FIG. 4 is a schematic illustration of the maximum height and maximum width of a thyroid nodule according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of coordinate points of interest of a breast nodule in accordance with an embodiment of the present invention;

FIG. 6 is a schematic view of a polygon formed by connecting lines of coordinate points of interest of a breast nodule according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of coordinate points of interest of a breast nodule in accordance with an embodiment of the present invention.

Detailed Description

The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.

The embodiment of the invention relates to a nodule aspect ratio extraction device, which can be used for quantifying the aspect ratio of a nodule to further help a doctor accurately judge the quality and the malignancy of the nodule,

in the first embodiment, thyroid nodules are taken as an example, and the following are concrete:

referring to fig. 1, the present embodiment includes:

an image acquisition module: for acquiring an ultrasound image with a nodule;

the interesting nodule image extraction module: the node boundary of the ultrasonic image is intercepted in a mode of selecting a plurality of interested coordinate points, so that an interested node image is obtained; FIG. 2 shows coordinate points of interest of thyroid nodules;

a polygonal nodule obtaining module: the system is used for connecting adjacent interested coordinate points in the interested nodule image to obtain a polygonal nodule; FIG. 3 shows a polygonal thyroid nodule;

nodule height and width calculation module: for calculating the maximum height and maximum width of the polygonal nodule;

a nodule aspect ratio calculation module: for calculating the aspect ratio of the polygon nodules from their maximum height and maximum width.

Further, the maximum height of the polygonal nodule is calculated in the nodule height and width calculation module according to the formula:wherein L is_H(x) Maxf (x) -minf (x); x is the abscissa of any vertical line of the polygonal nodule in the vertical direction; f (x) is a function with respect to x, which can be understood as f (x) representing the value of the ordinate at which the perpendicular with x as abscissa intersects the polygonal nodule, and defines f: N → NⁿAnd f (x) is defined as a multi-valued function (i.e., one or more output values are returned for each input), W being the polygon nodule width.

Further, the maximum width of the polygonal nodule is calculated in the nodule height and width calculation module according to the formula:wherein L is_W(y)＝maxf^-1(y)-minf^-1(y); y is the ordinate of an arbitrary horizontal line in the horizontal direction of the nodule image of interest, f^-1(y) is a function of y (i.e. the inverse of f (x)), which may be understood as f^-1(y) represents the value of the abscissa at the intersection of the horizontal line with y as the ordinate and the polygonal nodule, and f is defined^-1:N→Nⁿ(ii) a H is the polygon nodule height.

Referring to fig. 4, in the nodule good-and-malignant judging module, the aspect ratio of the nodule is calculated according to the maximum height and the maximum width of the polygonal nodule, and the good and malignant of the nodule is judged according to the aspect ratio of the nodule, if the maximum height of the polygonal nodule is greater than the maximum height of the polygonal noduleAnd maximum widthCalculating the aspect ratio of the nodule to satisfyThe thyroid nodule is greater than it is wide, i.e. the thyroid nodule may be at risk of malignancy; if the maximum height of the polygonal noduleAnd maximum widthCalculating the aspect ratio of the nodule to satisfyThe width of the thyroid nodule is greater than high, i.e., the thyroid nodule has a greater probability of being benign, where t is a preset constant.

It is worth mentioning that the value of t is very important, the shapes of nodules of different pathological structures are usually different, the embodiment is specific to thyroid nodules, and experiments show that t is 1, which is the most reasonable.

In the second embodiment, taking a breast nodule as an example, the details are as follows:

the modules used for judging the quality and the malignancy of the aspect ratio of the breast nodules and the functions of the modules are the same as those of the thyroid nodules, and the details are not repeated here. Fig. 5 shows the coordinate points of interest of a breast nodule, fig. 6 shows a polygonal breast nodule, and fig. 7 shows the aspect ratio of the breast nodule, and it can be seen from these figures that the thyroid nodule in the first embodiment is greatly different from the shape of the breast nodule in the second embodiment, so that nodules in different pathological regions cannot be treated in the same manner, that is, the thyroid nodule has the criterion of a thyroid nodule, the breast nodule has the criterion of a breast nodule, and the nodule aspect ratio judgment of different pathological parts is crucial for clinical judgment.

Based on the above analysis, the experimental analysis of t 1.18 in this embodiment is most reasonably effective for the subsequent determination of the aspect ratio of the breast nodules, specifically, if the maximum height of the polygonal nodulesAnd maximum widthCalculating the aspect ratio of the nodule to satisfyThe growth direction of the breast nodules is not parallel to the skin, i.e. the breast nodules may have a malignant risk; if the maximum height of the polygonal noduleAnd maximum widthCalculating the aspect ratio of the nodule to satisfyThen the breast nodule growth direction is considered parallel to the skin, i.e. a greater probability of the breast nodule being benign.

Nodules to which the present invention is applicable include, but are not limited to, thyroid nodules and breast nodules, which are just two embodiments to aid the reader in understanding.

Therefore, the method can quantitatively judge the nodule, effectively avoids errors caused by subjective judgment of the aspect ratio of the nodule, and improves the accuracy of good and malignant judgment of the nodule by taking the value of the aspect ratio of the nodule as a reference; the invention adopts different aspect ratio thresholds for nodules in different pathological parts, so that the invention is more reasonable and more standardized.