Dynamic rectal cancer radiotherapy effect monitoring system combined with iconography analysis

Abstract

The invention relates to the technical field of image motion analysis, in particular to a rectal cancer radiotherapy effect dynamic monitoring system combined with iconography analysis. Determining a reference recovery index representing the recovery effect from the dimensions of edge change and area change according to the characteristic that the lesion area becomes smaller and smaller along with the better and better treatment effect; then, based on the reference recovery index and in combination with the characteristic that rectum tissue circularity can cause gradual inward contraction of a lesion area and the edge is smoother and smoother, determining a more accurate shape recovery degree representing the reference recovery index; therefore, the corrected radiotherapy recovery curve is corrected more accurately according to the shape recovery degree, and dynamic monitoring of the rectal cancer radiotherapy effect is more visual and accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of image motion analysis, and particularly relates to a dynamic monitoring system for the radiotherapy effect of rectal cancer combined with imaging analysis. Background Art

[0002] Rectal cancer is a common malignant tumor of the digestive system, and radiotherapy is one of its main treatment methods. For experienced doctors, the radiotherapy effect is usually subjectively evaluated based on experience; however, for inexperienced medical students, it is relatively difficult to learn the evaluation of the radiotherapy effect. Therefore, in order to enable medical students to more intuitively learn and understand the radiotherapy effect of rectal cancer, a system that can dynamically understand the radiotherapy effect of rectal cancer is needed to assist medical students in learning and understanding.

[0003] The prior art usually adopts a machine learning-based method. Based on the characteristic that the lesion area of rectal cancer in CT images changes in gray scale during the radiotherapy process, the radiotherapy effect of rectal cancer is visually evaluated according to the gray scale change value of the lesion area. However, the degree of change in CT images of patients in different recovery periods is usually small, and the corresponding gray scale change is not easily captured. Moreover, the influence of the shape and area changes during the radiotherapy recovery process of rectal cancer on the radiotherapy effect is not considered, resulting in the dynamic monitoring of the radiotherapy effect of rectal cancer being not intuitive enough and having a poor monitoring effect. Summary of the Invention

[0004] In order to solve the technical problem that the gray scale change corresponding to the method of visually evaluating the radiotherapy effect of rectal cancer according to the gray scale change value of the lesion area is not easily captured, and the influence of the shape and area changes during the radiotherapy recovery process of rectal cancer on the radiotherapy effect is not considered, resulting in the dynamic monitoring of the radiotherapy effect of rectal cancer being not intuitive enough and having a poor monitoring effect, the purpose of this application is to provide a dynamic monitoring system for the radiotherapy effect of rectal cancer combined with imaging analysis. The specific technical solution adopted is as follows: This application proposes a dynamic monitoring system for the radiotherapy effect of rectal cancer combined with imaging analysis. The system includes: A data acquisition and preprocessing module, which is used to acquire the initial CT image of rectal cancer in the initial state and the CT recovery images of rectal cancer at each sampling moment during the radiotherapy treatment process; and determine the initial lesion area in the initial CT image of rectal cancer and the recovered lesion area in the CT recovery images of rectal cancer based on the image segmentation method; A first determination module, which is used to determine the matching recovery area of the initial lesion area according to the area intersection situation between the initial lesion area and the recovered lesion areas corresponding to other sampling moments; and determine the initial effect change curve of the initial lesion area according to the overall gray scale change situation of all the matching recovery areas; A second determination module, configured to determine the degree of diffusion recovery according to the overall trend of the edge change between the edge of the initial lesion region and each corresponding matching recovery region at each sampling moment; determine a reference recovery index according to the area reduction of each disease matching recovery region before each sampling moment and the degree of diffusion recovery. A radiotherapy effect monitoring module, configured to determine the degree of shape recovery according to the edge smoothness of the matching recovery region, the reference recovery index, and the circular approximation in shape; correct the initial effect change curve according to the degree of shape recovery to determine a corrected radiotherapy recovery curve; perform dynamic monitoring of the radiotherapy effect of rectal cancer according to the corrected radiotherapy recovery curve.

[0005] Further, the process of determining the initial lesion region in the initial rectal cancer CT image and the lesion recovery region in the rectal cancer CT recovery image based on the image segmentation method includes: Calculating the average significance value of each segmentation region in the initial rectal cancer CT image at all segmentation scales through the CA significance algorithm; taking the segmentation region whose normalized value of the average significance value is greater than a preset significance threshold as the initial lesion region; determining the lesion recovery region in the rectal cancer CT recovery image based on the acquisition process of the initial lesion region.

[0006] Further, the acquisition process of the matching recovery region includes: After mapping the rectal cancer CT recovery image at each sampling moment to the initial rectal cancer CT image, among all the lesion recovery regions corresponding to each sampling moment, taking the lesion recovery region with the largest overlapping area with the initial lesion region as the matching recovery region of the initial lesion region in each rectal cancer CT recovery image.

[0007] Further, the acquisition process of the initial effect change curve includes: Taking the mean gray value of all pixel points in the matching recovery region corresponding to the previous sampling moment of each matching recovery region as the comparison gray value of each matching recovery region; taking the mean gray value of all pixel points in each matching recovery region as the overall gray value; determining the gray value change of each matching recovery region according to the difference between the comparison gray value and the overall gray value; arranging the gray value changes of all the matching recovery regions of the initial lesion region in chronological order and performing curve fitting to determine the initial effect change curve of the initial lesion region.

[0008] Further, the acquisition process of the degree of diffusion recovery includes: Enlarge the area of each corresponding matching recovery region centered on the corresponding centroid in equal proportion to the area size of the corresponding initial lesion region to obtain the corresponding reference recovery region; After mapping the reference recovery region to the image where the corresponding initial lesion region is located, connect each boundary pixel point of the initial lesion region to the nearest boundary pixel point on the reference recovery region to obtain all first reference connection lines; all the intersection points obtained after extending all the first reference connection lines are used as the corresponding reference convergence points; Take the mean value of all the distances between all the reference convergence points corresponding to each matching recovery region as the corresponding convergence distance; Determine the diffusion recovery degree of each matching recovery region according to the convergence distance and the number of the reference convergence points.

[0009] Further, the process of determining the diffusion recovery degree of each matching recovery region according to the convergence distance and the number of the reference convergence points includes: Perform a negative correlation mapping on the product of the number of reference convergence points and the convergence distance to determine the diffusion recovery degree of each matching recovery region.

[0010] Further, the process of obtaining the reference recovery index includes: Perform a negative correlation mapping on the difference between the area of each matching recovery region corresponding to the initial lesion region and the area of the matching recovery region at the previous sampling moment to determine the area reduction index of each matching recovery region; normalize the product of the area reduction index and the diffusion recovery degree to determine the reference recovery index of each matching recovery region.

[0011] Further, the process of obtaining the shape recovery degree includes: Detect the number of corner points of each matching recovery region through a corner detection algorithm; take the product of the negative correlation mapping value of the number of corner points and the reference recovery index as the edge recovery index; Take the distance between each boundary pixel point in the matching recovery region and the corresponding centroid as the centroid distance of each boundary pixel point; calculate the centroid distance difference between each boundary pixel point and each other boundary pixel point; perform a negative correlation mapping on the mean value of all the centroid distance differences corresponding to all the boundary pixel points to determine the shape recovery index of the matching recovery region; Normalize the product of the shape recovery index and the edge recovery index to determine the shape recovery degree of the matching recovery region.

[0012] Further, the process of obtaining the corrected radiotherapy recovery curve includes: Correct the gray value change corresponding to the matching recovery region on the initial effect change curve according to the shape recovery degree, and determine the corrected change value of the matching recovery region. Arrange the corrected change values of all matching recovery regions of the initial lesion region in chronological order and perform curve fitting to determine the corrected radiotherapy recovery curve of the initial lesion region.

[0013] Furthermore, the process of obtaining the corrected change value includes: Take the product of the positive correlation mapping value of the shape recovery degree and the gray value change of the corresponding matching recovery region on the initial effect change curve as the corrected change value of the matching recovery region.

[0014] In a second aspect, the present application provides a computer device, including a memory and a processor. The memory is used to store computer program code, and the processor is used to call and run the computer program code from the memory to execute the system according to the first aspect or any embodiment of the first aspect of the present application.

[0015] In a third aspect, the present application provides a computer program product, where the computer program product includes computer program code, and when the computer program code is executed, it is used to execute the system according to the first aspect or any embodiment of the first aspect of the present application.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium, where the computer-readable storage medium stores computer program code, and when the computer program code is executed, it is used to execute the system according to the first aspect or any embodiment of the first aspect of the present application.

[0017] The present application has the following beneficial effects: The present application first determines the lesion region at each sampling moment based on saliency, then determines the matching recovery region of each lesion region at each sampling moment based on the intersection of the lesion regions, and determines the initial effect change curve in the initial state according to the gray value change of the matching recovery region. Further, according to the characteristics that radiotherapy will inhibit the spread of cancer cells and the edges will converge in the same direction towards the center with a more serious infection degree, and the lesion region will become smaller and smaller as the treatment effect gets better, the reference recovery index representing the recovery effect is determined from the dimensions of edge change and area change; then, based on the reference recovery index and the characteristics that the quasi-circularity of the rectal tissue will cause the lesion region to gradually contract inward and the edge to become smoother, the shape recovery degree representing the reference recovery index is determined more accurately; thus, the corrected radiotherapy recovery curve is corrected more accurately according to the shape recovery degree, making the dynamic monitoring of the radiotherapy effect of rectal cancer more intuitive and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0019] Figure 1 It is a structural block diagram of a dynamic monitoring system for the radiotherapy effect of rectal cancer by combined imaging analysis provided by an embodiment of the present invention; Figure 2 It is a schematic structural diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation manner, structure, features, and effects of a dynamic monitoring system for the radiotherapy effect of rectal cancer by combined imaging analysis proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0022] The following specifically describes the specific solution of a dynamic monitoring system for the radiotherapy effect of rectal cancer by combined imaging analysis provided by the present invention with reference to the accompanying drawings.

[0023] An embodiment of the present application provides a dynamic monitoring system for the radiotherapy effect of rectal cancer by combined imaging analysis. Please refer to Figure 1 , which shows a structural block diagram of a dynamic monitoring system for the radiotherapy effect of rectal cancer by combined imaging analysis provided by an embodiment of the present invention. The system includes: a data acquisition and preprocessing module 101, a first determination module 102, a second determination module 103, and a radiotherapy effect monitoring module 104.

[0024] The data acquisition and preprocessing module 101 is used to acquire the initial CT images of rectal cancer in the initial state and the restored CT images of rectal cancer at each sampling moment during the radiotherapy treatment process of rectal cancer; and determine the initial lesion area in the initial CT image of rectal cancer and the restored lesion area in the restored CT image of rectal cancer based on saliency.

[0025] First, acquire the CT images of rectal cancer obtained each time when a patient undergoes CT scans during the radiotherapy treatment process of rectal cancer and before the treatment. Among them, each sampling moment corresponds to the moment of each CT scan, that is, the sampling frequency is determined by the frequency of CT scans. It should be noted that the CT images of rectal cancer used for medical education in this application have been authorized by the patient for use, and will not be further elaborated hereinafter. In a specific implementation manner of the embodiment of the present invention, the CT image of rectal cancer obtained when the patient undergoes the last CT scan before the start of the radiotherapy treatment process of rectal cancer is used as the initial CT image of rectal cancer; the CT image of rectal cancer obtained when the patient undergoes CT scans during the radiotherapy treatment process of rectal cancer is used as the restored CT image of rectal cancer; by comparing and analyzing the acquired initial CT image of rectal cancer and the restored CT image of rectal cancer, it is convenient to more intuitively observe the treatment effect.

[0026] The gray value of the rectal cancer lesion area is larger than that of other normal areas, it is relatively white and has good integrity. Therefore, the lesion area, that is, the high-saliency area, can be divided by means of saliency detection. Preferably, in some possible implementation manners of the embodiment of the present invention, the process of determining the initial lesion area in the initial CT image of rectal cancer and the restored lesion area in the restored CT image of rectal cancer based on the image segmentation method includes: Calculate the average saliency value of each segmentation area in the initial CT image of rectal cancer at all segmentation scales through the CA saliency algorithm; the segmentation area whose normalized value of the average saliency value is greater than the preset saliency threshold is used as the initial lesion area; based on the acquisition process of the initial lesion area, determine the restored lesion area in the restored CT image of rectal cancer. Among them, the restored lesion area is the lesion area in the restored CT image of rectal cancer, and the initial lesion area is the lesion area in the initial CT image of rectal cancer. In a specific implementation manner of the embodiment of the present invention, the preset saliency threshold is set to 0.7, which can be adjusted according to the specific implementation environment, and the normalization method adopts linear normalization. It should be noted that the calculation of the average saliency belongs to the technical term in the CA saliency algorithm, and the CA saliency algorithm is a well-known technical means for those skilled in the art, and will not be further defined and elaborated herein.

[0027] In other specific implementation manners of the embodiments of the present invention, based on the object detection method, the initial rectal cancer CT image and the restored rectal cancer CT image are input into the trained object detection model, and the corresponding lesion regions are output. The lesion region segmented from the initial rectal cancer CT image is used as the initial lesion region, and the lesion region segmented from the restored rectal cancer CT image is used as the restored lesion region. In a specific implementation manner of the embodiments of the present invention, the object detection model selects the R-CNN model, which can be adjusted according to the specific implementation environment. The R-CNN model is a commonly used model in object detection and will not be elaborated further here.

[0028] The first determination module 102 is configured to determine the matching restored region of the initial lesion region according to the region intersection situation between the initial lesion region and the restored lesion regions corresponding to other respective sampling times; and determine the initial effect change curve of the initial lesion region according to the overall gray-scale change situation of all the matching restored regions.

[0029] Before analyzing the changes in the lesion region, it is first necessary to determine the respective changed restored lesion regions corresponding to the change of each initial lesion region in different restored rectal cancer CT images. Since during the recovery process of radiotherapy, the lesion spread of rectal cancer is restricted and its lesion region usually does not change greatly in position, in some possible implementation manners of the embodiments of the present invention, the process of obtaining the matching restored region includes: After mapping the restored rectal cancer CT image at each sampling time to the initial rectal cancer CT image, among all the restored lesion regions corresponding to each sampling time, the restored lesion region with the largest overlapping area with the initial lesion region is used as the matching restored region of the initial lesion region in each restored rectal cancer CT image. That is, the matching restored region is the lesion region at the corresponding position of the initial lesion region in the restored rectal cancer CT images at different sampling times, and the treatment effect or recovery effect of the corresponding initial lesion region can be analyzed through the change of the matching restored region.

[0030] In the case of the improvement of the condition during radiotherapy treatment, the gray scale of its lesion region will tend to be normal, that is, the gray scale will become smaller and smaller. And as the treatment continues, the recovery speed of the human body function is also constantly accelerating, thus affecting the decreasing trend of the gray scale value. That is, when the treatment effect is better and the gray scale value of the lesion region decreases faster, the corresponding gray scale change value will continuously increase, and the larger the gray scale change value, the better the treatment and recovery effect.

[0031] Preferably, in some possible implementation manners of the embodiments of the present invention, the process of obtaining the initial effect change curve includes: Restore the average gray value of all pixel points in the matching restoration area at the previous sampling moment corresponding to each matching restoration area, and use it as the comparison gray value of each matching restoration area; use the average gray value of all pixel points in each matching restoration area as the overall gray value; determine the gray value change of each matching restoration area according to the difference between the comparison gray value and the overall gray value; arrange the gray value changes of all matching restoration areas in the initial lesion area in chronological order and perform curve fitting to determine the initial effect change curve of the initial lesion area. For the initial effect change curve, since its vertical axis is the gray value change, the gray value change reflects the degree of gray reduction in the lesion area between adjacent sampling moments, and the degree of gray reduction reflects the treatment effect. Therefore, the initial effect change curve can intuitively reflect the radiotherapy effect of rectal cancer in the dimension of the overall change of gray value. It should be noted that curve fitting is a well-known technical means for those skilled in the art and will not be further defined and described here.

[0032] In a specific implementation manner of the embodiment of the present invention, the process of obtaining the gray value change is expressed by the formula: ; where is the gray value change of the matching restoration area corresponding to the th initial lesion area at the th sampling moment; is the overall gray value of the matching restoration area corresponding to the th initial lesion area at the th sampling moment, that is, the comparison gray value of the matching restoration area corresponding to the th sampling moment; is the overall gray value of the matching restoration area corresponding to the th initial lesion area at the th sampling moment. It should be noted that the matching restoration area at the first sampling moment is used to calculate the gray value change with the initial lesion area; in addition, for a patient, there is usually only one initial lesion area. To avoid the influence of contingency, this application calculates and analyzes with the th initial lesion area, so as to prevent the situation where it is impossible to calculate when there are multiple initial lesion areas.

[0033] The second determination module 103 is used to determine the diffusion restoration degree according to the overall trend of the edge change between the edge of the initial lesion area and each corresponding matching restoration area at each sampling moment; determine the reference restoration index according to the area reduction of each matching restoration area before each sampling moment and the diffusion restoration degree.

[0034] Since the degree of change in the CT images of patients in different recovery periods is usually small, and the corresponding gray-scale changes are not easily captured, the effect of reflecting the radiotherapy effect of rectal cancer based only on the initial effect change curve is poor. Therefore, it is necessary to further combine other aspects to conduct a more intuitive analysis of the radiotherapy effect of rectal cancer. After the cells of rectal cancer patients become cancerous, the cancerous area of the rectum spreads around the initial cancerous cells as the origin. During the process of improvement after radiotherapy, the spread of cancerous cells will be inhibited and the lesion area will gradually shrink, manifested as the lesion area gradually contracting inward, and the direction of convergence has a certain consistency.

[0035] Therefore, this application first analyzes the treatment effect according to the contraction characteristics during the recovery process; preferably, in some possible implementation manners of the embodiments of the present invention, the process of obtaining the degree of diffusion recovery includes: The area of each corresponding matching recovery region is proportionally enlarged with the corresponding centroid as the center to the area size of the corresponding initial lesion region to obtain the corresponding reference recovery region; after mapping the reference recovery region to the image where the corresponding initial lesion region is located, connect each boundary pixel point of the initial lesion region with the nearest boundary pixel point on the reference recovery region to obtain all the first reference connections; all the intersection points obtained after extending all the first reference connections are used as the corresponding reference convergence points; the mean value of all the distances between all the reference convergence points corresponding to each matching recovery region is used as the corresponding convergence distance; according to the convergence distance and the number of reference convergence points, determine the degree of diffusion recovery of each matching recovery region.

[0036] Since the direction of convergence during the recovery process conforms to the consistency feature, ideally, when the area of the matching recovery region is proportionally enlarged with the corresponding centroid as the center, the corresponding reference recovery region should be consistent with the corresponding initial lesion region. However, there are usually certain deviations in the implementation process. Combining the consistency of the convergence direction, the intersection points of the connection lines corresponding to the convergence directions of each edge point, that is, the first reference connection lines, will be closer. And the closer the corresponding intersection points are, the higher the consistency of the convergence direction and the better the consistency of the recovery degree; therefore, the smaller the convergence distance, the greater the degree of diffusion recovery representing the recovery effect; and when the number of reference convergence points is smaller, it means that the situation of intersection point coincidence is more, and the consistency of the convergence direction is better, then the corresponding degree of diffusion recovery representing the recovery effect should be greater; therefore, further determining the degree of diffusion recovery of each matching recovery region according to the convergence distance and the number of reference convergence points includes: performing a negative correlation mapping on the product of the number of reference convergence points and the convergence distance to determine the degree of diffusion recovery of each matching recovery region.

[0037] In a specific implementation manner of the embodiments of the present invention, the process of obtaining the degree of diffusion recovery is expressed by the formula: ; wherein, is the diffusion recovery degree of the th initial lesion region corresponding to the matching recovery region at the th sampling moment; is the mean value of all distances between all reference convergence points corresponding to the matching recovery region corresponding to the th initial lesion region at the th sampling moment, that is, the Euclidean distance between each reference convergence point and each other reference convergence point is statistically calculated, and the mean value of all Euclidean distances corresponding to all reference convergence points is used as the corresponding convergence distance; is the number of reference convergence points corresponding to the matching recovery region corresponding to the th initial lesion region at the th sampling moment. is an exponential function with the natural constant as the base. Implementers can adopt other negatively correlated mapping methods according to the specific implementation environment, such as , and reciprocal, wherein, is the hyperbolic tangent function, which will not be elaborated further here.

[0038] As the treatment effect gets better and better, the cancer cells of rectal cancer are controlled, the immune system begins to gradually return to normal, the lesion area will gradually decrease, and as the treatment progresses, the body gradually improves, and the area of the lesion area will decrease faster and faster. Therefore, based on the diffusion recovery degree, the area change of the lesion recovery area is combined to further analyze the treatment effect. Preferably, in some possible implementation manners of the embodiments of the present invention, the process of obtaining the reference recovery index includes: Performing a negatively correlated mapping on the difference between the area of each matching recovery region corresponding to the initial lesion region and the area of the matching recovery region at the previous sampling moment to determine the area reduction index of each matching recovery region; normalizing the product of the area reduction index and the diffusion recovery degree to determine the reference recovery index of each matching recovery region. Similar to the principle of the gray value change, the more the area of each matching recovery region decreases compared to the area of the matching recovery region at the previous sampling moment, the more it conforms to the characteristic that the area of the lesion area will decrease faster and faster when the treatment effect is good. Here, the area of each matching recovery region is subtracted from the area of the matching recovery region at the previous sampling moment. Therefore, it is necessary to perform a negatively correlated mapping on the corresponding difference and combine the diffusion recovery degree to obtain the reference recovery index representing the recovery effect of each matching recovery region.

[0039] In a specific implementation manner of the embodiments of the present invention, the process of obtaining the reference recovery index is expressed by the formula: ; wherein, is the reference recovery index of the matching recovery region corresponding to the th initial lesion region at the th sampling moment; is the degree of diffusion recovery of the matching recovery region corresponding to the th initial lesion region at the th sampling moment; The th initial lesion region at the th sampling moment corresponds to the area of the matching recovery region; is the area of the matching recovery region corresponding to the th initial lesion region at the th sampling moment; is the area reduction index of the matching recovery region corresponding to the th initial lesion region at the th sampling moment. When the area decreases, it is usually negative. After negative correlation mapping through the reciprocal of the exponential function with the natural constant as the base, the obtained area reduction index will take a positive value and is usually greater than 1; is a linear normalization function.

[0040] The radiotherapy effect monitoring module 104 is used to determine the shape recovery degree according to the edge smoothness of the matching recovery region, the reference recovery index, and the circular approximation in shape; correct the initial effect change curve according to the shape recovery degree to determine the corrected radiotherapy recovery curve; and dynamically monitor the radiotherapy effect of rectal cancer according to the corrected radiotherapy recovery curve.

[0041] Due to the quasi-circularity characteristics of the rectal tissue, as the treatment continues, its lesion area gradually shrinks inward and tends to disappear. And as the treatment progresses, the corresponding edge will gradually become smooth and the shape will approach a circle until it disappears; that is, for the matching recovery region at each sampling moment, the smoother and more circular the corresponding edge is, the greater the degree of regression of the lesion area and the better the treatment effect.

[0042] Preferably, in some possible implementation manners of the embodiments of the present invention, the process of obtaining the shape recovery degree includes: Detect the number of corner points in each matching recovery region through a corner detection algorithm; take the product of the negative correlation mapping value of the number of corner points and the reference recovery index as the edge recovery index. The more corner points there are, the less smooth the edge is. Therefore, after performing a negative correlation mapping on the number of corner points and multiplying it by the reference recovery index, the resulting edge recovery index characterizes the radiotherapy treatment effect. In a specific implementation manner of the embodiment of the present invention, the Harris corner detection algorithm is used for the corner detection algorithm, which can be adjusted according to the specific implementation environment, and the Harris corner detection algorithm is a well-known technical means in the art and will not be further limited and elaborated herein.

[0043] Take the distance between each boundary pixel point in the matching recovery region and the corresponding centroid as the centroid distance of each boundary pixel point; calculate the centroid distance difference between each boundary pixel point and every other boundary pixel point; perform a negative correlation mapping on the mean value of all the centroid distance differences corresponding to all boundary pixel points to determine the shape recovery index of the matching recovery region. For a circle, the length from a point on the boundary to the centroid point is the same, and the corresponding centroid distance differences are all 0. Therefore, the smaller the mean value of all the centroid distance differences corresponding to all pixel points, the better the corresponding recovery effect, that is, the larger the shape recovery index, the better the recovery effect. Finally, according to the relationship between the shape recovery index and the edge recovery index and the recovery effect, normalize the product of the shape recovery index and the edge recovery index to determine the shape recovery degree of the matching recovery region. It should be noted that the boundary pixel points are the pixel points located on the region boundary.

[0044] In a specific implementation manner of the embodiment of the present invention, the process of obtaining the shape recovery degree is expressed by the formula: ; where is the shape recovery degree of the matching recovery region corresponding to the th initial lesion region at the th sampling moment; is the number of corner points of the matching recovery region corresponding to the th initial lesion region at the th sampling moment; is the reference recovery index of the matching recovery region corresponding to the th initial lesion region at the th sampling moment; is the edge recovery index of the matching recovery region corresponding to the th initial lesion region at the th sampling moment; is the mean value of all the centroid distance differences corresponding to all boundary pixel points in the matching recovery region corresponding to the th initial lesion region at the th sampling moment; is the shape recovery index of the corresponding matching recovery region at the -th initial lesion region at the -th sampling moment. It should be noted that to ensure the significance of the calculation results, in the fractional operations of the embodiments of the present invention, when the denominator is 0, a tuning factor greater than 0 needs to be added to the denominator to prevent the denominator from being 0. The value of the tuning factor is set by the implementer according to the actual situation. In this application, it is set to 0.1.

[0045] The shape recovery degree combines the characterization of the radiotherapy effect of rectal cancer in terms of the boundary convergence direction, area change, edge smoothness, and regional circularity. Therefore, finally, the initial effect change curve can be corrected by the obtained shape recovery degree, so that the corrected radiotherapy recovery curve can more intuitively reflect the treatment effect, and thus the dynamic monitoring of the radiotherapy effect of rectal cancer can be more intuitive and accurate based on the corrected radiotherapy recovery curve.

[0046] Preferably, in some possible implementation manners of the embodiments of the present invention, the process of obtaining the corrected radiotherapy recovery curve includes: Correct the gray value change corresponding to the matching recovery region on the initial effect change curve according to the shape recovery degree to determine the corrected change value of the matching recovery region; arrange the corrected change values of all the matching recovery regions of the initial lesion region in chronological order and then perform curve fitting to determine the corrected radiotherapy recovery curve of the initial lesion region. Since the initial effect change curve is obtained by fitting the gray value changes of each matching recovery region, the shape recovery degree representing the recovery effect or treatment effect obtained from each matching recovery region is used as a weight to correct the gray value change, so as to achieve the purpose of correcting the curve.

[0047] Preferably, in a specific implementation manner of the embodiments of the present invention, the process of obtaining the corrected change value includes: taking the product of the positive correlation mapping value of the shape recovery degree and the gray value change of the corresponding matching recovery region on the initial effect change curve as the corrected change value of the matching recovery region. The reason for performing a positive correlation mapping on the shape recovery degree is that the value range of the shape recovery degree is from 0 to 1. If directly multiplied by the gray value change, it will only make the obtained corrected radiotherapy recovery curve less obvious. Therefore, a positive correlation mapping is needed to make the value of the shape recovery degree not less than 1. In a specific implementation manner of the embodiments of the present invention, the process of obtaining the corrected change value is expressed by the formula: ; where is the corrected change value of the matching recovery region corresponding to the -th initial lesion region at the -th sampling moment; is the -th initial lesion region at the The gray-scale change value of the corresponding matching recovery region at a sampling moment; For the th initial lesion region, the shape recovery degree of the corresponding matching recovery region at the th sampling moment; Through positive correlation mapping by adding 1 to the shape recovery degree, the corrected change value is always amplified compared to the gray-scale change value, thereby improving the intuitive degree of observing the treatment effect.

[0048] Finally, dynamic monitoring of the radiotherapy effect of rectal cancer is carried out according to the obtained corrected radiotherapy recovery curve. The curve can more intuitively monitor the radiotherapy effect of rectal cancer, and the form of the curve enables medical students to more intuitively learn and understand the radiotherapy effect of rectal cancer.

[0049] In summary, according to the characteristics that radiotherapy will inhibit the spread of cancer cells and the edges will converge in the same direction towards the center position with a more serious infection degree, and the lesion area will become smaller and smaller as the treatment effect gets better and better, this application determines the reference recovery index representing the recovery effect from the dimensions of edge change and area change; then, based on the reference recovery index and the characteristic that the quasi-circularity of rectal tissue will cause the lesion area to gradually contract inward and the edge to become smoother, the shape recovery degree more accurately representing the reference recovery index is determined; thus, the corrected radiotherapy recovery curve is more accurately corrected according to the shape recovery degree, making the dynamic monitoring of the radiotherapy effect of rectal cancer more intuitive and accurate.

[0050] The embodiment of this application also provides a computer device. Please refer to Figure 2 , which shows a schematic structural diagram of a computer device provided by an embodiment of the present invention. The computer device includes a memory 201, a processor 202, and a computer program 203 stored in the memory 201 and running on the processor 202. Among them, when the processor 202 executes the computer program 203, the computer device can execute any one of the dynamic monitoring systems for the radiotherapy effect of rectal cancer with combined imaging analysis introduced above.

[0051] The embodiment of this application also provides a computer program product. When the computer program product runs on a computer device, the computer device can execute any one of the dynamic monitoring systems for the radiotherapy effect of rectal cancer with combined imaging analysis introduced above.

[0052] The embodiment of this application also provides a computer-readable storage medium. Computer program code is stored in the computer-readable storage medium. When the computer program code runs on a computer device, the computer device can execute any one of the dynamic monitoring systems for the radiotherapy effect of rectal cancer with combined imaging analysis introduced above.

[0053] In the embodiments provided in the present application, it should be understood that the provided computer device, computer program product, and computer-readable storage medium are all used to execute the corresponding system provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the system provided above, and will not be elaborated here.

[0054] It should be noted that the above sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0055] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

Claims

1. A dynamic monitoring system for the radiotherapy effect of rectal cancer combined with imaging analysis, characterized in that The system includes: A data acquisition and preprocessing module, configured to acquire the initial CT images of rectal cancer in the initial state and the restored CT images of rectal cancer at each sampling moment during the radiotherapy treatment process of rectal cancer; determine the initial lesion region in the initial CT images of rectal cancer and the restored lesion region in the restored CT images of rectal cancer based on an image segmentation method; A first determination module, configured to determine the matching restored region of the initial lesion region according to the region intersection situation between the initial lesion region and the restored lesion regions corresponding to other respective sampling moments; determine the initial effect change curve of the initial lesion region according to the overall gray-scale change situation of all the matching restored regions; A second determination module, configured to determine the diffusion restoration degree at each sampling moment according to the overall edge change trend between the edge of the initial lesion region and the corresponding each matching restored region; determine the reference restoration index according to the area reduction situation of each matching restored region before each sampling moment and the diffusion restoration degree; A radiotherapy effect monitoring module, configured to determine the shape restoration degree according to the edge smoothness of the matching restored region, the reference restoration index, and the circular approximation situation in shape; correct the initial effect change curve according to the shape restoration degree to determine the corrected radiotherapy restoration curve; perform dynamic monitoring of the radiotherapy effect of rectal cancer according to the corrected radiotherapy restoration curve.

2. The dynamic monitoring system for the radiotherapy effect of rectal cancer with combined imaging analysis according to claim 1, characterized in that, The process of determining the initial lesion region in the initial CT images of rectal cancer and the restored lesion region in the restored CT images of rectal cancer based on the image segmentation method includes: Calculating the average significance value of each segmentation region in the initial CT images of rectal cancer at all segmentation scales through the CA significance algorithm; taking the segmentation region whose normalized value of the average significance value is greater than a preset significance threshold as the initial lesion region; determining the restored lesion region in the restored CT images of rectal cancer based on the acquisition process of the initial lesion region.

3. The dynamic monitoring system for the radiotherapy effect of rectal cancer with combined imaging analysis according to claim 1, characterized in that, The acquisition process of the matching restored region includes: After mapping the restored CT images of rectal cancer at each sampling moment to the initial CT images of rectal cancer, among all the restored lesion regions corresponding to each sampling moment, taking the restored lesion region with the largest overlapping area with the initial lesion region as the matching restored region of the initial lesion region in each restored CT image of rectal cancer.

4. The dynamic monitoring system for the radiotherapy effect of rectal cancer with combined imaging analysis according to claim 1, wherein, The acquisition process of the initial effect change curve includes: Taking the average gray-scale value of all pixel points in the matching restored region corresponding to the previous sampling moment of each matching restored region as the comparison gray-scale value of each matching restored region; taking the average gray-scale value of all pixel points in each matching restored region as the overall gray-scale value; determining the gray-scale change value of each matching restored region according to the difference between the comparison gray-scale value and the overall gray-scale value; arranging the gray-scale change values of all the matching restored regions of the initial lesion region in chronological order and performing curve fitting to determine the initial effect change curve of the initial lesion region.

5. The dynamic monitoring system for the radiotherapy effect of rectal cancer by combined imaging analysis according to claim 1, wherein The acquisition process of the diffusion restoration degree includes: Enlarge the area of each corresponding matching recovery region centered on the corresponding centroid proportionally to the area size of the corresponding initial lesion region to obtain the corresponding reference recovery region; After mapping the reference recovery region to the image where the corresponding initial lesion region is located, connect each boundary pixel point of the initial lesion region with the nearest boundary pixel point on the reference recovery region to obtain all first reference connection lines; all intersection points obtained after extending all the first reference connection lines are used as the corresponding reference convergence points; Take the mean of all distances between all reference convergence points corresponding to each matching recovery region as the corresponding convergence distance; Determine the diffusion recovery degree of each matching recovery region according to the convergence distance and the number of reference convergence points.

6. The dynamic monitoring system for the radiotherapy effect of rectal cancer by combined imaging analysis according to claim 5, characterized in that, The process of determining the diffusion recovery degree of each matching recovery region according to the convergence distance and the number of reference convergence points includes: Perform a negative correlation mapping on the product of the number of reference convergence points and the convergence distance to determine the diffusion recovery degree of each matching recovery region.

7. A dynamic monitoring system for the radiotherapy effect of rectal cancer by combined imaging analysis according to claim 1, characterized in that, The process of obtaining the reference recovery index includes: Perform a negative correlation mapping on the difference between the area of each matching recovery region corresponding to the initial lesion region and the area of the matching recovery region at the previous sampling moment to determine the area reduction index of each matching recovery region; normalize the product of the area reduction index and the diffusion recovery degree to determine the reference recovery index of each matching recovery region.

8. The dynamic monitoring system for the radiotherapy effect of rectal cancer by combined imaging analysis according to claim 1, characterized in that, The process of obtaining the shape recovery degree includes: Detect the number of corner points of each matching recovery region through a corner detection algorithm; take the product of the negative correlation mapping value of the number of corner points and the reference recovery index as the edge recovery index; Take the distance between each boundary pixel point in the matching recovery region and the corresponding centroid as the centroid distance of each boundary pixel point; calculate the difference in centroid distance between each boundary pixel point and every other boundary pixel point; perform a negative correlation mapping on the mean of all centroid distance differences corresponding to all boundary pixel points to determine the shape recovery index of the matching recovery region; Normalize the product of the shape recovery index and the edge recovery index to determine the shape recovery degree of the matching recovery region.

9. The dynamic monitoring system for the radiotherapy effect of rectal cancer with combined imaging analysis according to claim 4, characterized in that, The process of obtaining the corrected radiotherapy recovery curve includes: Correct the gray value change corresponding to the matching recovery region on the initial effect change curve according to the shape recovery degree to determine the corrected change value of the matching recovery region; Arrange the corrected change values of all matching recovery regions of the initial lesion region in chronological order and perform curve fitting to determine the corrected radiotherapy recovery curve of the initial lesion region.

10. The dynamic monitoring system for the radiotherapy effect of rectal cancer by combined imaging analysis according to claim 9, characterized in that, The process of obtaining the corrected change value includes: Take the product of the positive correlation mapping value of the shape recovery degree and the gray value change of the matching recovery region corresponding to the initial effect change curve as the corrected change value of the matching recovery region.

Images