CT image focus change analysis method and system based on time sequence

Abstract

The invention provides a CT image lesion change analysis method and system based on a time sequence, and relates to the technical field of lesion analysis. The method comprises the following steps: acquiring a CT image of a current examination of a patient, and acquiring a plurality of historical CT images of the patient; obtaining a lesion area where a lesion is located in the CT image through a lesion detection model; obtaining a historical lesion area where the lesion is located in the historical CT image through a lesion detection model; determining a focus state coefficient of the focus area and a historical focus state coefficient of the historical focus area; determining the development condition of the focus; and generating a focus change analysis report. According to the application, when the change condition of the lesion is determined to be analyzed, the lesion area in the CT image and the historical lesion area in the historical CT image are analyzed, and the lesion state coefficient and the historical lesion state coefficient are determined, so that the development condition of the lesion is determined. The accuracy of lesion development condition judgment is improved, and the lesion change analysis efficiency is improved.

Description

Technical Field

[0001] This application relates to the technical field of lesion analysis, and particularly to a method for analyzing the changes of lesions in CT images based on time series. Background Art

[0002] When designing a further treatment plan for cancer patients, it is necessary to analyze the changes in the patient's lesions. At this time, it can only rely on doctors spending a lot of time observing CT images and analyzing the changes in the patient's lesions according to the doctor's experience. The analysis speed is slow and depends on the doctor's experience. Therefore, there is a possibility that the analysis of the changes in the lesions is inaccurate, and problems such as low analysis efficiency are difficult to accurately judge the changes in the patient's lesions, resulting in low accuracy and efficiency in the analysis of the changes in the patient's lesions, affecting the further treatment of the patient. Summary of the Invention

[0003] This application provides a method for analyzing the changes of lesions in CT images based on time series, which can solve the technical problem that it is difficult to accurately judge the changes in the patient's lesions in the related art.

[0004] According to the first aspect of this application, a method for analyzing the changes of lesions in CT images based on time series is provided, including: After obtaining the CT image of the patient's current examination, obtain multiple historical CT images of the patient from the database; Detect the CT image through a lesion detection model to obtain the lesion area where the lesion is located in the CT image; Detect the historical CT image through a lesion detection model to obtain the historical lesion area where the lesion is located in the historical CT image; Determine the lesion status coefficient of the lesion area and the historical lesion status coefficient of the historical lesion area; Determine the development status of the lesion according to the lesion status coefficient, the historical lesion status coefficient, the examination time of the CT image, and the examination time of the historical CT image; Generate a lesion change analysis report according to the development status of the lesion.

[0005] According to this application, determining the lesion status coefficient of the lesion area includes: Determine the lesion size status coefficient of the lesion area according to the area of the lesion area and a preset lesion area threshold; Obtain the contour of the lesion area; Set multiple sampling points on the contour of the lesion area; Determine the sampling vectors between adjacent sampling points; Determine the lesion morphology status coefficient of the lesion area according to the sampling vectors; Determine the lesion shape status coefficient according to the lesion size status coefficient and the lesion morphology status coefficient; Determine the lesion density status coefficient of the lesion area according to the CT value of the centroid of the lesion area and the preset CT threshold value; Connect the centroid of the lesion area with the sampling point to obtain a detection line; Determine the lesion uniformity status coefficient of the lesion area according to the CT values of the pixel points on the detection line; Determine the lesion CT value status coefficient according to the lesion density status coefficient and the lesion uniformity status coefficient; Determine the lesion status coefficient according to the lesion shape status coefficient and the lesion CT value status coefficient.

[0006] According to the present application, determining the lesion shape status coefficient of the lesion area according to the sampling vector includes: According to the formula

[0007] Determine the lesion shape status coefficient of the lesion area , where is the coordinate of the (i + 1)-th sampling point, is the coordinate of the i-th sampling point, is the sampling vector between the (i + 1)-th sampling point and the i-th sampling point, is the coordinate of the (i - 1)-th sampling point, is the sampling vector between the i-th sampling point and the (i - 1)-th sampling point, is transpose vector of, n is the number of sampling points, min is the minimum value function, and both i and n are positive integers.

[0008] According to the present application, determining the lesion uniformity status coefficient of the lesion area according to the CT values of the pixel points on the detection line includes: Uniformly set a plurality of detection points on the detection line and determine the CT values of the detection points; Divide the detection points with the same serial number on each detection line into a group to obtain a plurality of detection point groups; Determine the lesion uniformity status coefficient of the lesion area according to the CT values of the detection points in the plurality of detection point groups.

[0009] According to the present application, determining the lesion uniformity status coefficient of the lesion area according to the CT values of the detection points in the plurality of detection point groups includes: Determine the average CT value of each detection point in the detection point group; Determine the standard deviation of the CT values of each detection point in the detection point group according to the average CT value of each detection point in the detection point group; Determine the coefficient of variation of the CT values of each detection point in the detection point group according to the standard deviation of the CT values and the average CT value; Determine the maximum value of the coefficient of variation corresponding to multiple detection point groups as the lesion uniformity state coefficient of the lesion area.

[0010] According to the present application, the lesion state coefficient includes a lesion shape state coefficient and a lesion CT value state coefficient, and the historical lesion state coefficient includes a historical lesion shape state coefficient and a historical lesion CT value state coefficient; Determine the lesion development status according to the lesion state coefficient, the historical lesion state coefficient, the examination time of the CT image, and the examination time of the historical CT image, including: According to the formula

[0011] Determine the lesion condition score of the CT image of this examination , where is the lesion shape state coefficient, is the lesion CT value state coefficient, and are preset weights; According to the formula

[0012] Determine the historical lesion condition score of the j-th historical CT image , where is the j-th historical lesion shape state coefficient, is the j-th historical lesion CT value state coefficient; Establish a coordinate system, and determine the coordinates of the lesion state coefficient and each historical lesion state coefficient in the coordinate system. Among them, the lesion shape state coefficient is the X value in the coordinates of the lesion state coefficient, the lesion CT value state coefficient is the Y value in the coordinates of the lesion state coefficient, the historical lesion shape state coefficient is the X value in the coordinates of the historical lesion state coefficient, and the historical lesion CT value state coefficient is the Y value in the coordinates of the historical lesion state coefficient; Determine the area to be rehabilitated in the coordinate system according to the lesion condition score; Determine the historical area to be rehabilitated in the coordinate system according to the historical lesion condition score; Determine the lesion development status according to the area to be rehabilitated and the historical area to be rehabilitated.

[0013] According to the present application, determining the area to be rehabilitated in the coordinate system according to the lesion condition score includes: Pass through the coordinates of the lesion state coefficient in the coordinate system, and make the current lesion condition equivalent line with a slope of ; Determine the area enclosed by the current lesion condition equivalent line, the X-axis, and the Y-axis as the area to be rehabilitated.

[0014] According to the present application, based on the area to be rehabilitated and the historical areas to be rehabilitated, the development status of the lesion is determined, including: According to the formula

[0015] the lesion development coefficient D is determined, where is the area of the area to be rehabilitated, is the area of the historical area to be rehabilitated corresponding to the (m - 1)-th historical CT image, is the examination time of the CT image, is the examination time of the (m - 1)-th historical CT image, m is the number of the current examination, is the area of the historical area to be rehabilitated corresponding to the (j + 1)-th historical CT image, is the area of the historical area to be rehabilitated corresponding to the j-th historical CT image, is the examination time of the (j + 1)-th historical CT image, is the examination time of the j-th historical CT image, max is the maximum value function, and both j and m are positive integers; Based on the lesion development coefficient, the development status of the lesion is determined.

[0016] According to the second aspect of the present application, a system for analyzing the changes of CT image lesions based on time series is provided, including: An image acquisition module, after acquiring the CT image of the patient's current examination, acquires multiple historical CT images of the patient in the database; A lesion area module, which detects the CT image through a lesion detection model to obtain the lesion area where the lesion is located in the CT image; A historical lesion area module, which detects the historical CT image through a lesion detection model to obtain the historical lesion area where the lesion is located in the historical CT image; A lesion status coefficient module, which determines the lesion status coefficient of the lesion area and the historical lesion status coefficient of the historical lesion area; A lesion development status module, which determines the development status of the lesion according to the lesion status coefficient, the historical lesion status coefficient, the examination time of the CT image, and the examination time of the historical CT image; A lesion change analysis report module, which generates a lesion change analysis report according to the development status of the lesion.

[0017] By adopting the above technical solutions, the present application can achieve the following technical effects: According to the present application, the CT image of the patient's current examination can be obtained and multiple historical CT images of the patient can be obtained. Through the lesion detection model, the CT image and the historical CT images are detected to obtain the lesion area where the lesion is located in the CT image and the historical lesion area where the lesion is located in the historical CT images, so as to determine the lesion status coefficient of the lesion area and the historical lesion status coefficient of the historical lesion area. Furthermore, based on the change situation of the historical lesion status coefficient and the lesion status coefficient, the lesion development condition is determined, and a lesion change analysis report is generated. This reduces the dependence on manpower, improves the accuracy of judging the lesion development condition, and improves the efficiency of lesion change analysis. When detecting the lesion area, the CT image of the patient's current examination and multiple historical CT images can be obtained, and based on the lesion detection model, the contour of the lesion area is detected from the CT image, so as to obtain the lesion area and the historical lesion area, providing accurate basic data for determining the lesion development condition. When determining the lesion status coefficient, the lesion size status coefficient of the lesion area can be determined based on the ratio of the area of the lesion area to the preset lesion area threshold. The contour of the lesion area can be determined according to the lesion detection model, and multiple sampling points are set on the contour of the lesion area in a uniformly angular manner, so as to determine the sampling vectors between adjacent sampling points. Then, based on the sampling vectors, the cosine value of the included angle between two adjacent sampling vectors at the most irregular position of the lesion shape is obtained, and according to the number of sampling points, the cosine value of the included angle between adjacent sampling vectors in the case of a completely regular lesion is determined, so as to obtain the lesion morphology status coefficient of the lesion area, enabling the lesion morphology status coefficient to accurately describe the regularity degree of the lesion shape. Furthermore, the lesion shape status coefficient is determined by weighted summation. Further, based on the ratio of the CT value of the centroid of the lesion area to the preset CT threshold, the lesion density status coefficient of the lesion area is determined, taking into account the situation that the preset CT threshold of the lesion is different for different human organs, improving the accuracy of the lesion density status coefficient. Based on the detection points uniformly set on the detection line, multiple groups of detection points are obtained, so as to obtain the dispersion coefficient of the CT values of each detection point in the group of detection points, and based on the relationship between the uniformity of the lesion area and the severity of the disease, the lesion uniformity status coefficient is obtained, improving the accuracy of the lesion uniformity status coefficient. Through weighted summation processing, the lesion CT value status coefficient is obtained, and then the lesion status coefficient is obtained, improving the accuracy, objectivity and comprehensiveness of the lesion status coefficient, enabling the lesion status coefficient to accurately describe the current state of the lesion. When determining the lesion development coefficient, the lesion condition score and the historical lesion condition score can be determined based on the lesion status coefficient, the historical lesion status coefficient, the examination time of the CT image and the examination time of the historical CT image. A coordinate system can be established, with the lesion shape status coefficient as the abscissa and the lesion CT value status coefficient as the ordinate, to determine the coordinates of the lesion condition score in the coordinate system, so as to determine the equivalent line of the current lesion condition, and then the area enclosed by the equivalent line and the coordinate axes is determined as the area to be rehabilitated.The situation where the equivalent changes occur in the lesion shape state coefficient and the lesion CT value state coefficient is considered, and the changes in the lesion shape state and the lesion CT value state can be observed simultaneously, improving the comprehensiveness of observation. Moreover, the change rate of the area to be rehabilitated and the maximum value of the change rate of the historical area to be rehabilitated can be determined, thereby determining the lesion development coefficient and further determining the lesion development status. The accuracy, comprehensiveness, and objectivity of the lesion development status are improved, and the efficiency of the lesion change analysis is enhanced. Brief Description of the Drawings

[0018] Figure 1 Exemplarily shown is a schematic flowchart of a method for analyzing the changes of lesions in CT images based on time series according to an embodiment of the present application; Figure 2 Exemplarily shown is a flowchart for determining the lesion state coefficient of a lesion area according to an embodiment of the present application; Figure 3 Exemplarily shown is a block diagram of a system for analyzing the changes of lesions in CT images based on time series according to an embodiment of the present application. Detailed Embodiments

[0019] Hereinafter, the technical solutions of the present application will be described in detail with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0020] Figure 1 Exemplarily shown is a schematic flowchart of a method for analyzing the changes of lesions in CT images based on time series according to an embodiment of the present application, and the method includes: Step S1, after obtaining the CT image of the patient's current examination, obtaining multiple historical CT images of the patient from the database; Step S2, detecting the CT image through a lesion detection model to obtain the lesion area where the lesion is located in the CT image; Step S3, detecting the historical CT images through a lesion detection model to obtain the historical lesion areas where the lesions are located in the historical CT images; Step S4, determining the lesion state coefficient of the lesion area and the historical lesion state coefficient of the historical lesion area; Step S5, determining the lesion development status according to the lesion state coefficient, the historical lesion state coefficient, the examination time of the CT image, and the examination time of the historical CT image; Step S6, generating a lesion change analysis report according to the lesion development status.

[0021] According to the embodiment of the present application, the method for analyzing the change of lesions in CT images based on time series can obtain the CT image of the patient's current examination and multiple historical CT images of the patient. By using a lesion detection model, the CT image and the historical CT images are detected to obtain the lesion area where the lesion is located in the CT image and the historical lesion area where the lesion is located in the historical CT images, thereby determining the lesion state coefficient of the lesion area and the historical lesion state coefficient of the historical lesion area. Furthermore, based on the change of the historical lesion state coefficient and the lesion state coefficient, the development status of the lesion is determined, and a lesion change analysis report is generated. This reduces the dependence on manpower, improves the accuracy of judging the development status of the lesion, and improves the efficiency of lesion change analysis.

[0022] According to the embodiment of the present application, in step S1, after obtaining the CT image of the patient's current examination, multiple historical CT images of the patient are obtained from the database. The patient can be examined every six months or one year, and a CT image is taken each time. After the patient's current examination and obtaining the CT image, all the CT images taken by the patient before this examination can be obtained from the hospital database, which are the multiple historical CT images of the patient.

[0023] According to the embodiment of the present application, in step S2, the CT image is detected by a lesion detection model to obtain the lesion area where the lesion is located in the CT image. The CT image is detected by a lesion detection model (such as Mask R-CNN, U-Net, etc.) to obtain the contour area of the lesion in the CT image, which is the lesion area where the lesion is located.

[0024] According to the embodiment of the present application, in step S3, the historical CT images are detected by a lesion detection model to obtain the historical lesion area where the lesion is located in the historical CT images. The historical CT images are detected by a lesion detection model (such as Mask R-CNN, U-Net, etc.) to obtain the contour area of the lesion in the historical CT images, which is the historical lesion area where the lesion is located. Alternatively, if the historical lesion area in the historical CT image has been obtained by a lesion detection model during past examinations and has been saved in the hospital database, the relevant information of the historical lesion area can be directly retrieved from the hospital database during this use.

[0025] In this way, the CT image of the patient's current examination and multiple historical CT images can be obtained, and based on the lesion detection model, the contour of the lesion area is detected in the CT image, thereby obtaining the lesion area and the historical lesion area, providing accurate basic data for determining the development status of the lesion.

[0026] Figure 2 Exemplarily shows a flowchart for determining the lesion state coefficient of the lesion area according to the embodiment of the present application.

[0027] According to an embodiment of the present application, in step S4, determining the lesion status coefficient of the lesion area and the historical lesion status coefficient of the historical lesion area includes: step S41, determining the lesion size status coefficient of the lesion area according to the area of the lesion area and a preset lesion area threshold; step S42, obtaining the contour of the lesion area; step S43, setting a plurality of sampling points on the contour of the lesion area; step S44, determining the sampling vectors between adjacent sampling points; step S45, determining the lesion morphology status coefficient of the lesion area according to the sampling vectors; step S46, determining the lesion shape status coefficient according to the lesion size status coefficient and the lesion morphology status coefficient; step S47, determining the lesion density status coefficient of the lesion area according to the CT value of the centroid of the lesion area and a preset CT threshold; step S48, connecting the centroid of the lesion area with the sampling points to obtain detection lines; step S49, determining the lesion uniformity status coefficient of the lesion area according to the CT values of the pixel points on the detection lines; step S410, determining the lesion CT value status coefficient according to the lesion density status coefficient and the lesion uniformity status coefficient; step S411, determining the lesion status coefficient according to the lesion shape status coefficient and the lesion CT value status coefficient.

[0028] According to an embodiment of the present application, in step S41, the lesion size status coefficient of the lesion area is determined according to the area of the lesion area and a preset lesion area threshold. The area of the lesion area can be determined according to the number of pixel points in the lesion area. Since some lesions are small and do not affect the development of the patient's lesions, therefore, when the area of the lesion area is greater than the preset lesion area threshold (for example, 0.5 square centimeters), attention needs to be paid and the impact of the current lesion on the development of the patient's lesions needs to be further considered. The ratio of the area of the lesion area to the preset lesion area threshold is the lesion size status coefficient of the lesion area. The larger the lesion size status coefficient, the larger the area of the lesion, and the greater the possibility that the lesion is a malignant tumor, and the more attention needs to be paid.

[0029] According to an embodiment of the present application, in step S42, the contour of the lesion area is obtained. By detecting the CT image through a lesion detection model (such as Mask R-CNN, U-Net, etc.), the contour of the lesion area can be directly determined.

[0030] According to an embodiment of the present application, in step S43, a plurality of sampling points are set on the contour of the lesion area. A ray can be emitted from the centroid of the contour of the lesion area in any direction, and with the centroid of the contour of the lesion area as the center, the ray is rotated. For each rotation of a certain angle, the intersection point of the ray and the contour of the lesion area is the sampling point. For example, rotating 360° with the centroid of the contour of the lesion area as the center, and setting the intersection point generated by the ray and the contour of the lesion area as a sampling point every 15° rotation, so that 24 sampling points can be set on the contour of the lesion area. The present application does not limit the specific number of sampling points.

[0031] According to an embodiment of the present application, in step S44, the sampling vectors between adjacent sampling points are determined. A vector can be determined for every two sampling points, which is the sampling vector. For example, when 24 sampling points are set on the contour of the lesion area, the sampling vector pointing from the first sampling point to the second sampling point, and the vector pointing from the second sampling point to the third sampling point can be determined, and so on.

[0032] According to an embodiment of the present application, in step S45, according to the sampling vectors, the lesion morphology state coefficient of the lesion area is determined, including: determining the lesion morphology state coefficient of the lesion area according to formula (1) , (1) Wherein, is the coordinate of the (i + 1)-th sampling point, is the coordinate of the i-th sampling point, is the sampling vector between the (i + 1)-th sampling point and the i-th sampling point, is the coordinate of the (i - 1)-th sampling point, is the sampling vector between the i-th sampling point and the (i - 1)-th sampling point, is the transposed vector of, n is the number of sampling points, min is the minimum value function, and both i and n are positive integers.

[0033] According to an embodiment of the present application, in formula (1), represents the cosine similarity between the sampling vector between the (i + 1)-th sampling point and the i-th sampling point, and the sampling vector between the i-th sampling point and the (i - 1)-th sampling point, that is, the cosine value of the angle between the sampling vector between the (i + 1)-th sampling point and the i-th sampling point, and the sampling vector between the i-th sampling point and the (i - 1)-th sampling point. Denote the minimum value of the above cosine value. Since the smaller the cosine value, the larger the corresponding included angle, therefore, the minimum value of the above cosine value can also be used as the cosine value corresponding to the maximum included angle between adjacent sampling vectors. Since the larger the included angle between two adjacent sampling vectors, the sharper and more irregular the shape of the lesion, therefore, the minimum value of the above cosine value can be used as the cosine value of the included angle between two adjacent sampling vectors at the position where the shape of the lesion is the most irregular. Since the shape of the lesion is circular under completely regular conditions, therefore, can represent the included angle between adjacent sampling vectors when the lesion is in a completely regular state. Therefore, represents the cosine value of the included angle between adjacent sampling vectors when the lesion is in a completely regular state. can represent the ratio of the cosine value of the included angle between two adjacent sampling vectors at the position where the shape of the lesion is the most irregular to the cosine value of the included angle between adjacent sampling vectors when the lesion is in a completely regular state. The smaller this ratio, the more irregular the shape of the lesion and the greater the possibility that the lesion will deteriorate into a malignant tumor. can be used as the lesion shape state coefficient. The larger the lesion shape state coefficient, the more irregular the shape of the lesion and the greater the possibility that the lesion will deteriorate into a malignant tumor, and the more attention needs to be paid.

[0034] According to an embodiment of the present application, in step S46, according to the lesion size state coefficient and the lesion shape state coefficient, determine the lesion appearance state coefficient. By performing weighted average processing on the lesion size coefficient and the lesion shape state coefficient, the lesion appearance state coefficient can be obtained. The larger the lesion appearance state coefficient, the worse the appearance state of the lesion and the more attention needs to be paid.

[0035] According to an embodiment of the present application, in step S47, according to the CT value of the centroid of the lesion area and the preset CT threshold, determine the lesion density state coefficient of the lesion area. The CT value of the centroid of the lesion area can represent the density at the center position of the lesion. When the lesion is in different human organs, the preset CT thresholds are also different. For example, when the lesion is in the liver, the preset CT threshold can be 30 HU, and when the lesion is in the brain, the preset CT threshold can be 40 HU. When the CT value of the lesion centroid is greater than the preset CT threshold, the density of the lesion is relatively large and it may be a malignant tumor. The lesion density state coefficient of the lesion area is the ratio of the CT value of the centroid of the lesion area to the preset CT threshold. The larger the lesion density state coefficient of the lesion area, the greater the density of the lesion and the greater the possibility that the lesion is a malignant tumor, and the more attention needs to be paid. The present application does not limit this.

[0036] According to an embodiment of the present application, in step S48, connect the centroid of the lesion area with a plurality of sampling points to obtain a plurality of detection lines. The detection lines are composed of the pixel points of the lesion area.

[0037] According to an embodiment of the present application, in step S49, according to the CT values of the pixel points on the detection line, determining the lesion uniformity state coefficient of the lesion area includes: evenly setting a plurality of detection points on the detection line and determining the CT values of the detection points; dividing the detection points with the same serial number on each detection line into a group to obtain a plurality of detection point groups; and determining the lesion uniformity state coefficient of the lesion area according to the CT values of the detection points in the plurality of detection point groups.

[0038] According to an embodiment of the present application, since the contour of the lesion area may be an irregular figure and the lengths of each obtained detection line are different, therefore, the same number of detection points can be evenly set on each detection line, and the CT value of each detection point can be obtained. For example, evenly setting 5 detection points on each detection line can divide each detection line into 6 equal parts. The serial numbers of the detection points on each detection line can be determined in the order from the centroid of the lesion area to the contour of the lesion area along the detection line, and the detection points with the same serial number on each detection line are divided into a group, which is the detection point group. The shape of the figure obtained by connecting the detection points of each detection point group is similar to the contour of the lesion area. The present application does not limit this.

[0039] According to an embodiment of the present application, determining the lesion uniformity state coefficient of the lesion area according to the CT values of the detection points in the plurality of detection point groups includes: determining the average CT value of each detection point in the detection point group; determining the standard deviation of the CT values of each detection point in the detection point group according to the average CT value of each detection point in the detection point group; determining the coefficient of variation of the CT values of each detection point in the detection point group according to the standard deviation of the CT values and the average CT value; and determining the maximum value of the coefficients of variation corresponding to the plurality of detection point groups as the lesion uniformity state coefficient of the lesion area.

[0040] According to an embodiment of the present application, the CT average value of each detection point in the detection point group is obtained through averaging processing, and according to the CT average value of each detection point in the detection point group, the standard deviation of the CT value of each detection point in the detection point group is determined. The ratio of the standard deviation of the CT value to the CT average value is the coefficient of variation of the CT value of each detection point group. The larger the coefficient of variation of the CT value of the detection point group, the greater the fluctuation of the CT value of the detection point group, the greater the fluctuation of the CT value on the closed curve formed by connecting the detection points in this group, and the more uneven the lesion. For example, cysts and other lesions may occur inside a malignant tumor, and there are obvious differences in the CT values between the area where the cyst is located and the area where the tumor cells are located. If the closed curve formed by connecting a certain group of detection points passes through the area where the cyst is located, the CT value of this group of detection points fluctuates greatly, and the coefficient of variation is also large. The maximum value of the coefficients of variation corresponding to multiple detection point groups can be determined as the lesion uniformity state coefficient of the lesion area, so as to describe the maximum fluctuation degree of the pixel points in the lesion area. The larger the lesion uniformity state coefficient, the more uneven the lesion, the greater the possibility that the lesion is a malignant tumor, and the more attention needs to be paid.

[0041] According to an embodiment of the present application, in step S410, according to the lesion density state coefficient and the lesion uniformity state coefficient, the lesion CT value state coefficient is determined. By performing weighted summation on the lesion density state coefficient and the lesion uniformity state coefficient, the lesion CT value state coefficient can be obtained. The larger the lesion CT value state coefficient, the greater the possibility that the lesion is a malignant tumor, the worse the CT value state of the lesion, and the more attention needs to be paid.

[0042] According to an embodiment of the present application, in step S411, according to the lesion shape state coefficient and the lesion CT value state coefficient, the lesion state coefficient is determined. By performing weighted summation on the lesion shape state coefficient and the lesion CT value state coefficient, the lesion condition score can be obtained. The larger the lesion condition score, the worse the lesion state, the greater the possibility that the lesion is a malignant tumor, and the more attention needs to be paid. Based on the same method as above, the historical lesion state coefficients of each historical CT image can be obtained.

[0043] In this way, the lesion size status coefficient of the lesion area can be determined based on the ratio of the area of the lesion area to the preset lesion area threshold. The contour of the lesion area can be determined according to the lesion detection model, and a plurality of sampling points can be set on the contour of the lesion area in a uniformly angular manner, so as to determine the sampling vectors between adjacent sampling points. Then, based on the sampling vectors, the cosine value of the included angle between two adjacent sampling vectors at the most irregular position of the lesion shape can be obtained, and according to the number of sampling points, the cosine value of the included angle between adjacent sampling vectors in the case of a completely regular lesion can be determined, so as to obtain the lesion morphology status coefficient of the lesion area, enabling the lesion morphology status coefficient to accurately describe the regularity of the lesion shape. Furthermore, the lesion appearance status coefficient is determined by weighted summation. Further, the lesion density status coefficient of the lesion area is determined according to the ratio of the CT value of the centroid of the lesion area to the preset CT threshold, taking into account the different preset CT thresholds for lesions located in different human organs, improving the accuracy of the lesion density status coefficient. Based on the detection points uniformly set on the detection line, a plurality of detection point groups are obtained, so as to obtain the dispersion coefficient of the CT values of each detection point in the detection point group, and based on the relationship between the uniformity of the lesion area and the severity of the disease, the lesion uniformity status coefficient is obtained, improving the accuracy of the lesion uniformity status coefficient. Through weighted summation processing, the lesion CT value status coefficient is obtained, and then the lesion status coefficient is obtained, improving the accuracy, objectivity and comprehensiveness of the lesion status coefficient, enabling the lesion status coefficient to accurately describe the current state of the lesion.

[0044] According to an embodiment of the present application, in step S5, the lesion status coefficient includes a lesion appearance status coefficient and a lesion CT value status coefficient, and the historical lesion status coefficient includes a historical lesion appearance status coefficient and a historical lesion CT value status coefficient; according to the lesion status coefficient, the historical lesion status coefficient, the inspection time of the CT image, and the inspection time of the historical CT image, the lesion development status is determined, including: determining the lesion condition score of the CT image of the current inspection according to formula (2) , (2) Wherein, is the lesion appearance status coefficient, is the lesion CT value status coefficient, and are preset weights; determining the historical lesion condition score of the jth historical CT image according to formula (3) , (3) Wherein, is the jth historical lesion appearance status coefficient, is the CT value status coefficient of the j-th historical lesion; establish a coordinate system, and determine the coordinates of the lesion status coefficient and each historical lesion status coefficient in the coordinate system. Among them, the lesion shape status coefficient is the X value in the coordinates of the lesion status coefficient, the lesion CT value status coefficient is the Y value in the coordinates of the lesion status coefficient, the historical lesion shape status coefficient is the X value in the coordinates of the historical lesion status coefficient, and the historical lesion CT value status coefficient is the Y value in the coordinates of the historical lesion status coefficient; determine the area to be rehabilitated in the coordinate system according to the lesion condition score; determine the historical area to be rehabilitated in the coordinate system according to the historical lesion condition score; determine the development status of the lesion according to the area to be rehabilitated and the historical area to be rehabilitated.

[0045] According to an embodiment of the present application, in formula (2), represents the weighted sum of the lesion shape status coefficient and the lesion CT value status coefficient, and can be used as the lesion condition score of the CT image in this examination. Similarly, in formula (3), represents the weighted sum of the j-th historical lesion shape status coefficient and the j-th historical lesion CT value status coefficient, and the historical lesion condition score of the j-th historical CT image can be obtained. The larger the lesion condition score, the worse the condition of the lesion, the greater the possibility that the lesion is a malignant tumor, and the more attention needs to be paid. Based on the comparison of the lesion condition score and the historical lesion condition score, the development status of the lesion can be determined. For example, it can be judged whether the lesion is deteriorating or improving.

[0046] According to an embodiment of the present application, establish a rectangular coordinate system, use the lesion shape status coefficient as the X value in the coordinates, and the lesion CT value status coefficient as the Y value in the coordinates to determine the coordinates of each lesion status coefficient. Similarly, use the historical lesion shape status coefficient as the X value in the coordinates, and the historical lesion CT value status coefficient as the Y value in the coordinates to determine the coordinates of each historical lesion status coefficient.

[0047] According to an embodiment of the present application, determining the area to be rehabilitated in the coordinate system according to the lesion condition score includes: passing through the coordinates of the lesion status coefficient in the coordinate system, making a current lesion condition equivalent line with a slope of ; determining the area enclosed by the current lesion condition equivalent line, the X-axis and the Y-axis as the area to be rehabilitated. In the lesion condition score, there may be a situation where the lesion shape status coefficient and the lesion CT value status coefficient change, but the obtained lesion condition score is the same as the historical lesion condition score of the previous examination, that is, the lesion condition score remains unchanged, but the lesion shape status coefficient and the lesion CT value status coefficient are different from the previous examination. Therefore, the coordinates with the same lesion condition score can be used with a slope of Connect them with straight lines to obtain the equivalent straight line of the current lesion condition. On the equivalent straight line of the lesion condition, the lesion condition scores of each point are the same, but the lesion shape state coefficient and the lesion CT value state coefficient are different. The triangular area enclosed by the equivalent straight line of the current lesion condition and the X-axis and Y-axis is the area to be rehabilitated. When the equivalent straight line of the current lesion condition passes through the coordinate origin, it means that both the lesion shape state coefficient and the lesion CT value state coefficient are 0, and the patient has fully recovered without an area to be rehabilitated. Similarly, the historical area to be rehabilitated in the coordinate system can be determined according to the historical lesion condition scores. The larger the area of the area to be rehabilitated, the more serious the patient's lesion condition and the more attention needs to be paid. Similarly, the historical area to be rehabilitated corresponding to the historical lesion condition scores can also be determined.

[0048] According to an embodiment of the present application, based on the area to be rehabilitated and the historical area to be rehabilitated, the development status of the lesion is determined, including: determining the lesion development coefficient D according to formula (4), (4) where, is the area of the area to be rehabilitated, is the area of the historical area to be rehabilitated corresponding to the (m - 1)-th historical CT image, is the inspection time of the CT image, is the inspection time of the (m - 1)-th historical CT image, m is the number of this inspection, is the area of the historical area to be rehabilitated corresponding to the (j + 1)-th historical CT image, is the area of the historical area to be rehabilitated corresponding to the j-th historical CT image, is the inspection time of the (j + 1)-th historical CT image, is the inspection time of the j-th historical CT image, max is the maximum value function, and both j and m are positive integers; the development status of the lesion is determined according to the lesion development coefficient.

[0049] According to an embodiment of the present application, in formula (4), represents the difference between the area of the area to be rehabilitated and the area of the historical area to be rehabilitated corresponding to the (m - 1)-th historical CT image, where the area of the area to be rehabilitated is the area of the area to be rehabilitated corresponding to the m-th CT image. represents the difference between the inspection time of the CT image and the inspection time of the (m - 1)-th historical CT image, where the inspection time of the CT image is the inspection time of the m-th CT image. Therefore, can represent the change rate of the area of the area to be rehabilitated. The larger the change rate of the area of the area to be rehabilitated, the faster the development of the lesion and the more attention needs to be paid. Similarly, can represent the change rate of the areas of the historical areas to be rehabilitated corresponding to the j-th historical CT image and the (j + 1)-th historical CT image. Therefore, can represent the maximum value of the change rate of the area of the historical area to be rehabilitated corresponding to each historical CT image. The ratio of the change rate of the area of the area to be rehabilitated to the maximum value of the change rate of the area of the historical area to be rehabilitated corresponding to each historical CT image can be used as a lesion development coefficient. According to the lesion development coefficient, the development status of the lesion, such as whether it is deteriorating, recovering, or unchanged, can be judged. For example, if the lesion development coefficient is large (e.g., greater than 1), it means that the change rate of the current area to be rehabilitated has changed significantly relative to the change rate of the area of the historical area to be rehabilitated, and the lesion is deteriorating rapidly, which requires attention and timely treatment measures. If the lesion development coefficient is greater than 0 and less than or equal to 1, it means that the change rate of the current area to be rehabilitated is relatively small compared to the change rate of the area of the historical area to be rehabilitated, and the lesion is still developing towards a serious situation, but the development speed is slow. If the lesion development coefficient is equal to 0, it means that the lesion has stopped developing and the condition is stable. If the lesion development coefficient is less than 0, it means that the lesion is getting better.

[0050] In this way, based on the lesion status coefficient, the historical lesion status coefficient, the inspection time of the CT image, and the inspection time of the historical CT image, the lesion status score and the historical lesion status score can be determined. A coordinate system can be established, with the lesion shape status coefficient as the abscissa and the lesion CT value status coefficient as the ordinate, to determine the coordinates of the lesion status score in the coordinate system, thereby determining the equivalent line of the current lesion status, and then determining the area enclosed by the equivalent line and the coordinate axes as the area to be rehabilitated. Considering the case of equivalent changes in the lesion shape status coefficient and the lesion CT value status coefficient, the changes in both the lesion shape status and the lesion CT value status can be observed simultaneously, improving the comprehensiveness of the observation. Moreover, the change rate of the area to be rehabilitated and the maximum value of the change rate of the historical area to be rehabilitated can be determined, thereby determining the lesion development coefficient and further determining the lesion development status. This improves the accuracy, comprehensiveness, and objectivity of the lesion development status, and improves the efficiency of lesion change analysis.

[0051] According to an embodiment of the present application, in step S6, a lesion change analysis report is generated according to the lesion development status. The lesion change analysis report may include information such as the condition is getting better, the review frequency can be reduced, the condition is deteriorating, the review frequency needs to be increased, and treatment measures need to be taken.

[0052] A method for analyzing the changes of lesions in CT images based on time series according to an embodiment of the present application can obtain the CT image of the patient's current examination and multiple historical CT images of the patient. By using a lesion detection model, the CT image and the historical CT images are detected to obtain the lesion area where the lesion is located in the CT image and the historical lesion area where the lesion is located in the historical CT images. Thus, the lesion status coefficient of the lesion area and the historical lesion status coefficient of the historical lesion area are determined. Furthermore, based on the changes in the historical lesion status coefficient and the lesion status coefficient, the development status of the lesion is determined, and a lesion change analysis report is generated. This reduces the dependence on manpower, improves the accuracy of judging the development status of the lesion, and improves the efficiency of lesion change analysis. When detecting the lesion area, the CT image of the patient's current examination and multiple historical CT images can be obtained, and based on the lesion detection model, the contour of the lesion area is detected from the CT image, so as to obtain the lesion area and the historical lesion area, providing accurate basic data for determining the development status of the lesion. When determining the lesion status coefficient, the lesion size status coefficient of the lesion area can be determined based on the ratio of the area of the lesion area to a preset lesion area threshold. The contour of the lesion area can be determined according to the lesion detection model, and a plurality of sampling points are set on the contour of the lesion area in a uniformly angular manner, so as to determine the sampling vectors between adjacent sampling points. Then, based on the sampling vectors, the cosine value of the included angle between two adjacent sampling vectors at the most irregular position of the lesion shape is obtained, and according to the number of sampling points, the cosine value of the included angle between adjacent sampling vectors in the case of a completely regular lesion is determined, so as to obtain the lesion morphology status coefficient of the lesion area, enabling the lesion morphology status coefficient to accurately describe the degree of regularity of the lesion shape. Furthermore, the lesion shape status coefficient is determined by weighted summation. Further, based on the ratio of the CT value of the centroid of the lesion area to a preset CT threshold, the lesion density status coefficient of the lesion area is determined, taking into account the situation that the preset CT threshold of the lesion is different for different human organs, improving the accuracy of the lesion density status coefficient. Based on the detection points uniformly set on the detection line, a plurality of detection point groups are obtained, so as to obtain the dispersion coefficient of the CT values of each detection point in the detection point group, and based on the relationship between the uniformity of the lesion area and the severity of the disease, the lesion uniformity status coefficient is obtained, improving the accuracy of the lesion uniformity status coefficient. Through weighted summation processing, the lesion CT value status coefficient is obtained, and then the lesion status coefficient is obtained, improving the accuracy, objectivity and comprehensiveness of the lesion status coefficient, enabling the lesion status coefficient to accurately describe the current state of the lesion. When determining the lesion development coefficient, the lesion condition score and the historical lesion condition score can be determined based on the lesion status coefficient, the historical lesion status coefficient, the examination time of the CT image, and the examination time of the historical CT image.A coordinate system can be established, with the lesion shape status coefficient as the abscissa and the lesion CT value status coefficient as the ordinate, to determine the coordinates of the lesion condition score in the coordinate system, thereby determining the equivalent line of the current lesion condition, and further determining the area enclosed by the equivalent line and the coordinate axes as the area to be rehabilitated. Considering the case of equivalent changes in the lesion shape status coefficient and the lesion CT value status coefficient, it is possible to simultaneously observe the changes in the lesion shape status and the lesion CT value status, improving the comprehensiveness of the observation. Moreover, the change rate of the area to be rehabilitated and the maximum value of the change rate of the historical area to be rehabilitated can be determined, thereby determining the lesion development coefficient and further determining the lesion development status. This improves the accuracy, comprehensiveness, and objectivity of the lesion development status and the efficiency of lesion change analysis.

[0053] Figure 3 Exemplarily shown is a block diagram of a CT image lesion change analysis system based on time series according to an embodiment of the present application. The system includes: An image acquisition module, after acquiring the CT image of the patient's current examination, acquires multiple historical CT images of the patient in the database; A lesion area module, which detects the CT image through a lesion detection model to obtain the lesion area where the lesion is located in the CT image; A historical lesion area module, which detects the historical CT image through a lesion detection model to obtain the historical lesion area where the lesion is located in the historical CT image; A lesion status coefficient module, which determines the lesion status coefficient of the lesion area and the historical lesion status coefficient of the historical lesion area; A lesion development status module, which determines the lesion development status according to the lesion status coefficient, the historical lesion status coefficient, the examination time of the CT image, and the examination time of the historical CT image; A lesion change analysis report module, which generates a lesion change analysis report according to the lesion development status.

[0054] The present application can be a method, apparatus, system, and / or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions thereon for performing various aspects of the present application.

[0055] Those skilled in the art should understand that the embodiments of the present application described above and shown in the drawings are only examples and do not limit the present application. The objectives of the present application have been fully and effectively achieved. The functions and structural principles of the present application have been demonstrated and explained in the embodiments. Without departing from the said principles, the embodiments of the present application can have any deformation or modification.

[0056] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for analyzing the changes of lesions in CT images based on time series, characterized in that, Including: After obtaining the CT image of the patient's current examination, obtain multiple historical CT images of the patient from the database; Detect the CT image through a lesion detection model to obtain the lesion area where the lesion is located in the CT image; Detect the historical CT images through a lesion detection model to obtain the historical lesion areas where the lesions are located in the historical CT images; Determine the lesion status coefficient of the lesion area and the historical lesion status coefficient of the historical lesion area; Determine the lesion development status according to the lesion status coefficient, the historical lesion status coefficient, the examination time of the CT image, and the examination time of the historical CT image; Generate a lesion change analysis report according to the lesion development status.

2. The method for analyzing the change of lesions in CT images based on time series according to claim 1, wherein, Determine the lesion status coefficient of the lesion area, including: Determine the lesion size status coefficient of the lesion area according to the area of the lesion area and a preset lesion area threshold; Obtain the contour of the lesion area; Set multiple sampling points on the contour of the lesion area; Determine the sampling vectors between adjacent sampling points; Determine the lesion morphology status coefficient of the lesion area according to the sampling vectors; Determine the lesion shape status coefficient according to the lesion size status coefficient and the lesion morphology status coefficient; Determine the lesion density status coefficient of the lesion area according to the CT value of the centroid of the lesion area and a preset CT threshold; Connect the centroid of the lesion area with the sampling points to obtain detection lines; Determine the lesion uniformity status coefficient of the lesion area according to the CT values of the pixel points on the detection lines; Determine the lesion CT value status coefficient according to the lesion density status coefficient and the lesion uniformity status coefficient; Determine the lesion status coefficient according to the lesion shape status coefficient and the lesion CT value status coefficient.

3. The method for analyzing the changes of CT image lesions based on time series according to claim 2, characterized in that, Determine the lesion morphology status coefficient of the lesion area according to the sampling vectors, including: According to the formula ； Determine the lesion morphological state coefficient of the lesion area , where is the coordinate of the (i + 1)-th sampling point, is the coordinate of the i-th sampling point, is the sampling vector between the (i + 1)-th sampling point and the i-th sampling point, is the coordinate of the (i - 1)-th sampling point, is the sampling vector between the i-th sampling point and the (i - 1)-th sampling point, is 's transposed vector, n is the number of sampling points, min is the minimum value function, and both i and n are positive integers.

4. The method for analyzing the change of lesions in CT images based on time series according to claim 2, wherein, Determine the lesion uniformity status coefficient of the lesion area according to the CT values of the pixel points on the detection lines, including: Uniformly set multiple detection points on the detection lines and determine the CT values of the detection points; Divide the detection points with the same serial number on each detection line into a group to obtain multiple groups of detection points; Determine the lesion uniformity status coefficient of the lesion area according to the CT values of the detection points in the multiple groups of detection points.

5. The method for analyzing the change of lesions in CT images based on time series according to claim 4, wherein, Determine the lesion uniformity status coefficient of the lesion area according to the CT values of the detection points in the multiple groups of detection points, including: Determine the CT average value of each detection point in the group of detection points; Determine the CT value standard deviation of each detection point in the group of detection points according to the CT average value of each detection point in the group of detection points; Determine the coefficient of variation of the CT values of each detection point in the group of detection points according to the CT value standard deviation and the CT average value; Determine the maximum value of the coefficients of variation corresponding to the multiple groups of detection points as the lesion uniformity status coefficient of the lesion area.

6. The method for analyzing the change of CT image lesions based on time series according to claim 2, wherein The lesion status coefficient includes a lesion shape status coefficient and a lesion CT value status coefficient, and the historical lesion status coefficient includes a historical lesion shape status coefficient and a historical lesion CT value status coefficient; Determine the lesion development status according to the lesion status coefficient, the historical lesion status coefficient, the examination time of the CT image, and the examination time of the historical CT image, including: According to the formula ； Determine the lesion status score of the CT image for this examination , where is the lesion shape status coefficient, is the lesion CT value status coefficient, and are preset weights; According to the formula ； Determine the historical lesion status score of the j-th historical CT image , where is the shape status coefficient of the j-th historical lesion, is the CT value status coefficient of the j-th historical lesion; Establish a coordinate system and determine the coordinates of the lesion status coefficient and each historical lesion status coefficient in the coordinate system. Among them, the lesion shape status coefficient is the X value in the coordinates of the lesion status coefficient, the lesion CT value status coefficient is the Y value in the coordinates of the lesion status coefficient, the historical lesion shape status coefficient is the X value in the coordinates of the historical lesion status coefficient, and the historical lesion CT value status coefficient is the Y value in the coordinates of the historical lesion status coefficient; Determine the area to be rehabilitated in the coordinate system according to the lesion condition score; Determine the historical area to be rehabilitated in the coordinate system according to the historical lesion condition score; Determine the lesion development status according to the area to be rehabilitated and the historical area to be rehabilitated; 7. The method for analyzing the changes of CT image lesions based on time series according to claim 6, wherein Determine the area to be rehabilitated in the coordinate system according to the lesion condition score, including: Through the coordinates of the lesion state coefficient in the coordinate system, make a current lesion condition equivalent line with a slope of ; Determine the area enclosed by the equivalent straight line of the current lesion condition, the X-axis and the Y-axis as the area to be rehabilitated; 8. The method for analyzing changes in CT image lesions based on time series according to claim 6, characterized in that Determine the lesion development status according to the area to be rehabilitated and the historical area to be rehabilitated, including: According to the formula ； Determine the lesion development coefficient D, where, is the area of the area to be rehabilitated, is the area of the historical area to be rehabilitated corresponding to the (m - 1)-th historical CT image, is the inspection time of the CT image, is the inspection time of the (m - 1)-th historical CT image, and m is the number of this inspection, is the area of the historical area to be rehabilitated corresponding to the (j + 1)-th historical CT image, is the area of the historical area to be rehabilitated corresponding to the j-th historical CT image, is the inspection time of the (j + 1)-th historical CT image, is the inspection time of the j-th historical CT image, max is the maximum value function, and both j and m are positive integers; Determine the lesion development status according to the lesion development coefficient; 9. A time-series based CT image lesion change analysis system for performing the method as described in claims 1-8, characterized in that, Including: An image acquisition module, after acquiring the CT image of the patient's current examination, acquires multiple historical CT images of the patient in the database; A lesion area module, which detects the CT image through a lesion detection model to obtain the lesion area where the lesion is located in the CT image; A historical lesion area module, which detects the historical CT image through a lesion detection model to obtain the historical lesion area where the lesion is located in the historical CT image; A lesion status coefficient module, which determines the lesion status coefficient of the lesion area and the historical lesion status coefficient of the historical lesion area; A lesion development status module, which determines the lesion development status according to the lesion status coefficient, the historical lesion status coefficient, the examination time of the CT image, and the examination time of the historical CT image; A lesion change analysis report module, which generates a lesion change analysis report according to the lesion development status.

Images