Method and system for monitoring cervical cancer cell reproduction inhibition state of traditional Chinese medicine

Abstract

The invention relates to the technical field of cell state monitoring, in particular to a method and system for monitoring the cervical cancer cell reproduction inhibition state through traditional Chinese medicine. In order to monitor the change rule of cancer cells in the experimental process of inhibiting the reproduction state of cervical cancer cells by traditional Chinese medicine, a flat micro-culture device convenient for 24-hour comprehensive monitoring is firstly arranged, so that the microscopic image of each cancer cell can be conveniently and comprehensively observed, then the similarity is calculated and compared with a similarity threshold value, and the change rule of the cancer cells can be monitored. The cancer cells at all moments are in one-to-one correspondence in a manner of numbering the cancer cells, so that the state change rule of each cancer cell in the experiment process can be locked, the fineness of experiment data is further improved, and deep research and curative effect quantitative evaluation of the traditional Chinese medicine anti-cervical cancer mechanism are better realized; the technical problem that an existing algorithm is difficult to stably track evolution of the same cell along with time is solved, and deep research and curative effect quantitative evaluation of a traditional Chinese medicine anti-cervical cancer mechanism are better achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of cell state monitoring, and in particular to a monitoring method and system for the inhibition of cervical cancer cell proliferation by traditional Chinese medicine. Background Art

[0002] In recent years, the anti-cancer potential of traditional Chinese medicine ingredients has attracted much attention. In studies on cervical cancer, a traditional Chinese medicine compound containing curcumin has shown potential therapeutic effects, but the dynamic evaluation of its effects still faces technical bottlenecks. Existing monitoring methods mostly rely on intermittent microscopic observations or endpoint detection, which makes it difficult to achieve 24-hour uninterrupted cell status tracking, resulting in the inability to fully capture the real-time reproduction dynamics, migration behavior, and response patterns of cancer cells under drug intervention.

[0003] In addition, traditional microscopic image analysis technology has significant deficiencies in dealing with cell overlap, morphological changes and long-term data association. For example, cells may be confused in identity recognition due to division, movement or occlusion during the culture process. Existing algorithms are difficult to stably track the time evolution of the same cells, which in turn affects the accuracy of statistical data. This defect seriously restricts the in-depth research on the anti-cervical cancer mechanism of traditional Chinese medicine and the quantitative evaluation of its efficacy. Summary of the invention

[0004] In view of the deficiencies of the prior art, the present invention provides a monitoring method and system for the inhibition of cervical cancer cell proliferation by traditional Chinese medicine, which solves the technical problem that the existing algorithm is difficult to stably track the evolution of the same cell over time.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: A monitoring method for the inhibition of cervical cancer cell proliferation by traditional Chinese medicine includes a flat micro-culture device for culturing cervical cancer cells. The detection method specifically includes the following steps: S1, acquiring a microscopic image of the cancer cells in a direction perpendicular to the flat surface of the micro-culture device, and pre-processing the microscopic image to identify the cancer cells; S2, determining whether the current moment is the first moment of the microscopic image; If yes, then the cancer cell data of each cancer cell is obtained, and different numbers are assigned to each cancer cell to obtain the cancer cell number and then the process ends; If not, proceed to step S3; S3, obtaining cancer cell data of each cancer cell at any time, and calculating the similarity between the cancer cell data at the current time and the cancer cell rectangular frame of each cancer cell data in history; S4, setting a similarity threshold, and determining whether the similarity value is greater than the similarity threshold; If so, extract the cancer cell number of the cancer cell data in the history with the largest similarity value, and assign it to the cancer cell data at the current moment; If not, a new cancer cell number is assigned to the cancer cell data at the current moment; S5. Output monitoring data according to cancer cell data, cancer cell numbers and preset statistical rules.

[0006] Preferably, in step S2, the specific steps of acquiring cancer cell data are as follows: S21, establishing an initial rectangular frame for each cancer cell according to a target detection algorithm, and obtaining a cancer cell boundary line; S22, select any edge of the rectangular box and mark it as an active edge, and mark the remaining edges as passive edges; S23, making the active edge tangent to the cancer cell boundary line and obtaining the tangent point, making the passive edge intersect with the cancer cell boundary line and having only one intersection point; S24, moving the cutting point along the cancer cell boundary line, and obtaining a rectangular frame with the smallest area and only one intersection between the active edge and the cancer cell boundary line, and marking it as the cancer cell rectangular frame; S25, sequentially obtaining two mutually perpendicular sides of each edge of the cancer cell rectangular frame, and a first intersection point between the two perpendicular sides and the cancer cell boundary line; S26, obtaining the length of the cancer cell boundary line closest to the frame edge between the two first intersection points, and using it as the virtual length of the frame edge; S27. According to the frame size, angle, position and virtual length of each frame edge of the cancer cell rectangular frame, construct an expression of the cancer cell rectangular frame to obtain cancer cell data; the expression of the cancer cell rectangular frame is as follows: ; In the above formula, and The first and second markers represent the rectangular frame of the cancer cell, respectively. and Respectively represent the horizontal and vertical coordinates of the center point of the cancer cell rectangle. and Respectively represent the width and length of the cancer cell rectangle, where Corresponding to the longest side of the cancer cell rectangular box, S is the data set of the virtual length of the cancer cell boundary line corresponding to each box edge, Indicates the minimum angle that the X-axis passes when it is rotated to be parallel to the edge corresponding to any data in the data set. .

[0007] Preferably, in step S24, the following steps are specifically included: S241, randomly setting a number of sampling points on the cancer cell boundary line, and moving the cutting point along the boundary line for one circle to obtain a number of first rectangular frames when the cutting point is located at the sampling point; S242, selecting a first rectangular frame where the active edge and the cancer cell boundary have two or more intersection points, and marking it as a second rectangular frame; S243, rotating the active edge of the second rectangular frame, and determining whether a rectangular frame having only one intersection point between the active edge and the cancer cell boundary line can be obtained; If yes, rotate the active edge of the second rectangular frame to obtain a new rectangular frame with the smallest area, and mark it as the first rectangular frame; If not, the second rectangular frame and the corresponding sampling points are removed; S244, selecting a first rectangular box with the smallest area and having only one intersection point between the active edge and the cancer cell boundary line, and calculating the absolute value of the area difference between the first rectangular box and the first rectangular box obtained last time; S245, determining whether the absolute value of the area difference is less than the area difference threshold; If yes, the current first rectangular frame is marked as a cancer cell rectangular frame, and then the process goes to step S25; If not, proceed to the next step; S246, selecting a sampling point corresponding to the first rectangular frame with the smallest area, and marking two sampling points adjacent to the sampling point as segmentation points; S247, setting a number of sampling points again between the two segmentation points, and moving the cutting point along the cancer cell boundary line between the two segmentation points, and then returning to step S242.

[0008] Preferably, in step S245, the area difference threshold is 1.0% of the area of ​​the first rectangular frame with the smallest area obtained last time.

[0009] Preferably, in step S241, the steps of setting the sampling points are: S2411, randomly setting a number of initial sampling points on the cancer cell boundary line; S2412, obtaining each convex hull on the cancer cell boundary line; S2413, calculating the ratio of the depth to the arc length of each convex hull in sequence; S2414, setting a depth-to-length ratio threshold, and eliminating convex hulls whose depth-to-arc length ratio is less than the depth-to-length ratio threshold, to obtain a standard convex hull; S2415. Set sampling points at the vertices, starting point, and end point of the standard convex hull.

[0010] Preferably, the number of the initial sampling points is greater than or equal to 12.

[0011] Preferably, in step S3, the following steps are specifically included: S31, rotating the angles of the cancer cell rectangular frames of each cancer cell data at the current moment and in the history to the same angle with the center point as the center, and the angle is a multiple of 90°; S32, calculating the IOU value of the cancer cell rectangular frame corresponding to the converted cancer cell data at the current moment and each cancer cell data in the history; the calculation formula of the IOU value is: ; In the above formula, A and B represent the cancer cell rectangular frame corresponding to the cancer cell data at the current moment and any cancer cell data in the history, respectively. and They represent the horizontal and vertical coordinates of the center point of the cancer cell rectangle A, respectively. and Respectively represent the width and length of the cancer cell rectangle A, and They represent the horizontal and vertical coordinates of the center point of the cancer cell rectangle B, and represent the width and length of object B respectively, and Respectively represent the horizontal and vertical overlap between the cancer cell rectangle A and the cancer cell rectangle B, represents the overlapping area of ​​cancer cell rectangular box A and cancer cell rectangular box B, and Respectively represent the area of ​​cancer cell rectangular box A and cancer cell rectangular box B, Represents the IOU value of cancer cell rectangular box A and cancer cell rectangular box B; S33, calculating the similarity between the cancer cell data at the current moment and any cancer cell data in the history according to the IOU value and the cancer cell data; the similarity calculation formula is: ; In the above formula, Indicates similarity, and denote the first coefficient and the second coefficient respectively, Represents the standard deviation of the difference between the data in the data set of the virtual length in the cancer cell rectangular box A and the corresponding data in the data set of the virtual length in the cancer cell rectangular box B.

[0012] Preferably, in step S4, the following steps are specifically included: S41, setting a similarity threshold, and determining whether the similarity value is greater than the similarity threshold; If so, the cancer cell number of the cancer cell data in the history with the largest similarity value is extracted and marked as the candidate number for the current cancer cell data, and then the next step is entered; If not, proceed to step S43; S42, determining whether a cancer cell number that is the same as the candidate number of the current cancer cell data appears at the previous moment; If yes, the candidate number is used as the cancer cell number of the current cancer cell data, and then the process goes to step S5; If not, proceed to the next step; S43, determining whether the cancer cell border of the current cancer cell data has an intersection with other cancer cell data; If yes, the cancer cell data is marked as cancer cell data to be classified, and no cancer cell number is assigned to the cancer cell data, and then the process goes to step S5; If not, proceed to the next step; S44, determining whether the similarity value between the current cancer cell data and the historical cancer cell data is greater than a similarity threshold; If so, the cancer cell number of the cancer cell data in the history with the largest similarity value is extracted and marked as the candidate number for the current cancer cell data, and then the next step is entered; If not, a new cancer cell number is assigned to the cancer cell data at the current moment, and then the next step is entered; S45, starting from the current moment, sequentially calculating the similarity values ​​of the cancer cell rectangular frames corresponding to the cancer cell data at each moment and the cancer cell data to be classified at the previous moment; S46, determining whether the similarity value is greater than a similarity threshold; If yes, then extract the cancer cell number of the cancer cell data with the largest similarity value, and assign it to the corresponding cancer cell data to be classified at the previous moment, and then proceed to the next step; If not, proceed to the next step.

[0013] Preferably, the cancer cell number is a positive integer, and each time a new cancer cell number is assigned to the cancer cell data at the current moment, the new cancer cell number is 1 greater than the maximum cancer cell number that has been generated.

[0014] The present invention also provides a monitoring system for the Chinese medicine inhibition of the proliferation status of cervical cancer cells, comprising a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the monitoring method for the Chinese medicine inhibition of the proliferation status of cervical cancer cells is implemented.

[0015] By means of the above technical solution, the present invention provides a monitoring method and system for inhibiting the proliferation of cervical cancer cells by traditional Chinese medicine, which has at least the following beneficial effects: 1. In order to monitor the changing patterns of cancer cells during the experimental process of inhibiting the proliferation of cervical cancer cells with traditional Chinese medicine, the present invention firstly sets a flat micro-culture device for 24-hour comprehensive monitoring, so as to facilitate comprehensive observation of the microscopic images of each cancer cell, and then calculates the similarity, compares it with the similarity threshold, and assigns cancer cells numbers to correspond the cancer cells at each moment one by one, so as to lock the state change pattern of each cancer cell during the experiment, further improve the granularity of the experimental data, and better realize the in-depth study of the anti-cervical cancer mechanism of traditional Chinese medicine and the quantitative evaluation of the efficacy.

[0016] 2. In order to prevent the high probability of two or more morphologically similar cancer cells appearing when there are a large number of cancer cells, which may lead to incorrect similarity determination and incorrect cancer cell tracking, the present invention combines the virtual lengths corresponding to the rectangular frame and the frame edge to comprehensively evaluate the similarity of cancer cells from two aspects, thereby making it more accurate.

[0017] 3. In view of the limited computing power of hardware in the laboratory, the present invention reduces the laboratory's requirements for hardware performance by setting the initial number of sampling points, and further subdividing and setting sampling points at key positions while ensuring computing power and data accuracy, making it more universal.

[0018] 4. The present invention further arranges steps S41 to S46 to realize the identification of cancer cells that reappear after being blocked and newly proliferated cancer cells, and assigns cancer cell numbers, thereby realizing the tracking of the morphology and trajectory changes of various cancer cells.

[0019] 5. The present invention makes the cancer cell number a positive integer, and each time a new cancer cell number is assigned to the cancer cell data at the current moment, the new cancer cell number is 1 greater than the cancer cell number with the largest value that has been generated. This allows for a clearer understanding of the number of newly proliferated cancer cells, the number of cancer cell deaths, and the changing pattern of cancer cell volume, etc., based on the changes in the values ​​of the cancer cell numbers. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 This is a flow chart of the monitoring method of the Chinese medicine for inhibiting the proliferation of cervical cancer cells of the present invention; Figure 2 This is a diagram of cervical cancer cells; Figure 3 A schematic diagram of virtual length. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0022] Curcumin is a polyphenolic substance extracted from traditional Chinese medicine plants such as turmeric, zedoary turmeric, and turmeric. It has attracted much attention for its multiple pharmacological effects such as anti-inflammatory, antioxidant, anti-tumor, and antibacterial. Curcumin has been found to have a significant inhibitory effect on tumor development in the progression of cervical cancer. In recent years, a large number of in vitro and in vivo studies have found that curcumin can play a therapeutic role in the treatment of cervical cancer by promoting cell apoptosis, inhibiting tumor cell proliferation, metastasis and invasion, inhibiting the integration of HPV with host cells, and inducing tumor cell autophagy. Curcumin has a wide range of mechanisms of action on cervical cancer and may become a new anti-tumor drug in the future. However, due to the poor water solubility, rapid decomposition, and low bioavailability of curcumin, there is still much room for exploration in the research of curcumin derivatives and new preparations. Existing studies have found that curcumin has a therapeutic effect on cervical cancer. Reports show that curcumin has the possibility of binding to E6 protein. Therefore, it is necessary to explore the role of curcumin in sensitizing cervical cancer and its possible molecular mechanism. We proposed the following hypothesis and demonstrated it: curcumin and LOC644656 competitively bind to ZNF143 protein, resulting in ZNF143 being unable to be guided by LOC644656 to bind to the E6-AP promoter region, blocking the ubiquitination of p53 protein by the LOC644656 / ZNF143 / E6-AP signaling axis, and enhancing the drug sensitivity of cervical cancer to cisplatin.

[0023] Therefore, in order to more stably track the time evolution of the same cancer cells and improve the accuracy of statistical data, the present invention provides a monitoring method for inhibiting the proliferation of cervical cancer cells with traditional Chinese medicine, such as Figure 1 As shown, the in-depth study of the mechanism of Chinese medicine against cervical cancer and the quantitative evaluation of its efficacy are achieved, including a flat micro-culture device for culturing cervical cancer cells. The detection method specifically includes the following steps: S1. Obtain a microscopic image of cancer cells in a direction perpendicular to the flat surface of the micro-culture device, and pre-process the microscopic image to identify cancer cells. The thickness of the culture space in the micro-culture device is between the minimum diameter of a single cervical cancer cell and the maximum diameter of two cervical cancer cells, and is generally set between 20 microns and 60 microns. The diameter of a single cervical cancer cell is usually between 20 microns and 30 microns. Common micro-culture devices are mainly microfluidic chips, which are processed to form a culture space extending in the horizontal direction. During the culture process, the cancer cells inside are observed in the vertical direction. The pre-processing methods include support vector machine methods, methods based on watershed algorithms, GVF Snake models, and rough sets.

[0024] S2, determining whether the current moment is the first moment of the microscopic image; If yes, then the cancer cell data of each cancer cell is obtained, and different numbers are assigned to each cancer cell to obtain the cancer cell number and then the process ends; If not, proceed to step S3; The acquisition of cancer cell data is to facilitate the tracking of cancer cells. At each moment, the cancer cell data at that moment is compared with the cancer cell data at the previous moment, so as to determine the correspondence between the cancer cells at this moment and the cancer cells at the previous moment, and to achieve cancer cell tracking. However, when the number of cancer cells is large, the probability of cancer cells with similar morphology is high, which may result in errors in similarity determination, leading to cancer cell tracking errors. Therefore, the method of obtaining cancer cell data is refined to reduce the probability of misidentification. The specific steps for obtaining cancer cell data are as follows: S21, establishing an initial rectangular frame for each cancer cell according to a target detection algorithm, and obtaining a cancer cell boundary line. The target detection algorithm may adopt a commonly used YOLO algorithm, etc.; S22, select any edge of the rectangular box and mark it as an active edge, and mark the remaining edges as passive edges; S23, making the active edge tangent to the cancer cell boundary line and obtaining the tangent point, making the passive edge intersect with the cancer cell boundary line and having only one intersection point; S24, moving the cut point along the cancer cell boundary line, and obtaining a rectangular frame with the smallest area and only one intersection between the active edge and the cancer cell boundary line, marking it as a cancer cell rectangular frame. By obtaining the cancer cell rectangular frame with the smallest area, the correlation between the size of the cancer cell rectangular frame and the morphological characteristics of the cancer cell itself can be strengthened, which is convenient for subsequent determination based on similarity. The acquisition of the cancer cell rectangular frame specifically includes the following steps: S241. Several sampling points are randomly set on the cancer cell boundary line, and the cut point is moved along the boundary line for one circle to obtain several first rectangular frames when the cut point is located at the sampling point. The setting of the sampling points needs to meet both the computing power requirements of the monitoring system hardware and the accuracy requirements of the monitoring data. The steps for setting the sampling points are as follows: S2411. Several initial sampling points are randomly set on the boundary line of cancer cells. A large number of experiments have shown that the common morphological features of cervical cancer cells (depression, lobed edges) require at least 8 directions of detection. When the number of sampling points is equal to 12, more than 85% of the boundary information can be maintained. Therefore, it is best to make the number of initial sampling points greater than or equal to 12.

[0025] S2412, obtaining each convex hull on the border line of the cancer cell. Points on the convex hull will cause a significant change in the size and position of the rectangular frame, so they are used as key positions to subsequently establish the rectangular frame; S2413, calculating the ratio of the depth to the arc length of each convex hull in sequence to eliminate noise data; S2414. Set a depth-to-length ratio threshold, and remove convex hulls whose depth-to-arc length ratio is less than the depth-to-length ratio threshold to obtain a standard convex hull. The depth-to-length ratio threshold is generally set to 0.05.

[0026] S2415. Set sampling points at the vertices, starting point, and end point of the standard convex hull.

[0027] S242, selecting a first rectangular frame where the active edge and the cancer cell boundary have two or more intersection points, and marking it as a second rectangular frame; S243, rotating the active edge of the second rectangular frame, and determining whether a rectangular frame having only one intersection point between the active edge and the cancer cell boundary line can be obtained; If yes, rotate the active edge of the second rectangular frame to obtain a new rectangular frame with the smallest area, and mark it as the first rectangular frame; If not, the second rectangular frame and the corresponding sampling points are removed; S244, selecting a first rectangular box with the smallest area and having only one intersection point between the active edge and the cancer cell boundary line, and calculating the absolute value of the area difference between the first rectangular box and the first rectangular box obtained last time. The reason for calculating the absolute value is mainly that the volume of the cancer cells may increase or decrease during the culture process, so the influence of the positive and negative signs of the result is removed by calculating the absolute value; S245, determining whether the absolute value of the area difference is less than the area difference threshold; according to experiments, the area change of the first rectangular frame of the cervical cancer cells at two adjacent moments does not exceed 1.0% of the first rectangular frame at the previous moment, so the area difference threshold is set to 1.0% of the area value of the first rectangular frame obtained last time; If yes, the current first rectangular frame is marked as a cancer cell rectangular frame, and then the process goes to step S25; If not, proceed to the next step; S246, selecting the sampling point corresponding to the first rectangular frame with the smallest area, and marking two sampling points adjacent to the sampling point as segmentation points, at which point the sampling point corresponding to the final rectangular frame with the smallest area is located on the cancer cell boundary line between the two segmentation points.

[0028] S247, set several sampling points again between the two segmentation points, take more detailed samples, and move the cutting point along the cancer cell boundary line between the two segmentation points, and then return to step S242. In this process, if the computing power of the hardware is sufficient, a large number of sampling points can be set at one time, so there is no need to perform further sampling point setting in the subsequent steps S241-S247.

[0029] S25, sequentially obtaining two mutually perpendicular sides of each edge of the cancer cell rectangular frame, and a first intersection point between the two perpendicular sides and the cancer cell boundary line; S26, obtaining the length of the cancer cell boundary line closest to the frame edge between the two first intersection points, and using it as the virtual length of the frame edge, such as Figure 3 As shown, the two mutually perpendicular sides of the A frame edge are the B frame edge and the D frame edge respectively, the two first intersection points of the B frame edge and the D frame edge with the cancer cell boundary line are intersection point 3 and intersection point 1 respectively, the cancer cell boundary line between intersection point 1 and intersection point 3 has two segments, the length of the cancer cell boundary line closest to the frame edge (i.e., the A frame edge) is taken as the virtual length of the A frame edge, and the virtual lengths of the A, B, C, and D frame edges can be obtained by this method; S27. According to the frame size, angle, position and virtual length of each frame edge of the cancer cell rectangular frame, construct an expression of the cancer cell rectangular frame to obtain cancer cell data; the expression of the cancer cell rectangular frame is as follows: ; In the above formula, and The first and second markers represent the rectangular frame of the cancer cell, respectively. and Respectively represent the horizontal and vertical coordinates of the center point of the cancer cell rectangle. and Respectively represent the width and length of the cancer cell rectangle, where Corresponding to the longest side of the cancer cell rectangular box, S is a data set of the virtual length of the cancer cell boundary line corresponding to each box edge. The virtual length corresponding to 1-4 edges can be selected as the data in the data set. Indicates the minimum angle that the X-axis passes when it is rotated to be parallel to the edge corresponding to any data in the data set. For example, the X-axis is rotated until it is parallel to the L side with the longest length of the cancer cell boundary line.

[0030] S3, obtaining cancer cell data of each cancer cell at any time, calculating the similarity between the cancer cell data at the current time and the cancer cell rectangular frame of each cancer cell data in history. Since there are a large number of cancer cells in the micro-culture device, if the similarity is judged only by the size of the cancer cell rectangular frame, the probability of misjudgment is relatively high. At this time, in order to improve its accuracy, the similarity calculation is further combined with the data set of the virtual length corresponding to the frame edge of the cancer cell rectangular frame, and the morphological characteristics of the boundary line of the cancer cell are included in the calculation factor of the similarity, which specifically includes the following steps: S31, rotating the angles of the cancer cell rectangular boxes of each cancer cell data at the current moment and in the history to the same angle with the center point as the center, and the angle is a multiple of 90°, so that the sides of the cancer cell rectangular boxes are either parallel or perpendicular to the x-axis, thereby facilitating the accurate calculation of the subsequent IOU value; S32, calculate the IOU value of the cancer cell rectangular frame corresponding to the converted cancer cell data at the current moment and each cancer cell data in the history. In the actual monitoring process, in order to reduce the amount of calculation, only the cancer cell data at the current moment can be compared with the historical cancer cell data within a certain range centered on the cancer cell and the IOU value can be calculated. The historical cancer cells within a certain radius from the current cancer cell are selected through the coordinates of the current cancer cell center and the preset radius. The calculation formula of the IOU value is: ; In the above formula, A and B represent the cancer cell rectangular frame corresponding to the cancer cell data at the current moment and any cancer cell data in the history, respectively. and They represent the horizontal and vertical coordinates of the center point of the cancer cell rectangle A, respectively. and Respectively represent the width and length of the cancer cell rectangle A, and They represent the horizontal and vertical coordinates of the center point of the cancer cell rectangle B, and represent the width and length of object B respectively, and Respectively represent the horizontal and vertical overlap between the cancer cell rectangle A and the cancer cell rectangle B, represents the overlapping area of ​​cancer cell rectangular box A and cancer cell rectangular box B, and Respectively represent the area of ​​cancer cell rectangular box A and cancer cell rectangular box B, Represents the IOU value of cancer cell rectangular box A and cancer cell rectangular box B; S33, calculating the similarity between the cancer cell data at the current moment and any cancer cell data in the history according to the IOU value and the cancer cell data; the similarity calculation formula is: ; In the above formula, Indicates similarity, and denote the first coefficient and the second coefficient respectively, The standard deviation of the difference between the data in the data set of the virtual length of the cancer cell rectangular box A and the corresponding data in the data set of the virtual length of the cancer cell rectangular box B is calculated first, that is, the difference between the data in the data set of the virtual length of the cancer cell rectangular box A and the corresponding data in the data set of the virtual length of the cancer cell rectangular box B is calculated, and then the standard deviation of the difference is calculated. .

[0031] S4, setting a similarity threshold, and determining whether the similarity value is greater than the similarity threshold; If so, extract the cancer cell number of the cancer cell data in the history with the largest similarity value, and assign it to the cancer cell data at the current moment; If not, a new cancer cell number is assigned to the cancer cell data at the current moment. During the monitoring process, it is found that some cancer cells will be blocked by another cancer cell and disappear, or even move with the blocked cancer cell. After a period of time, the blocked cancer cell may reappear, or the cancer cell will die directly during the blocking period. It is necessary to identify such cancer cells to ensure the consistency of the cancer cell number of the same cancer cell during the monitoring process, which specifically includes the following steps: S41, setting a similarity threshold, and judging whether the similarity value between the current cancer cell data and the cancer cell data in the history is greater than the similarity threshold. The similarity threshold is generally set between 0.5 and 0.9, and can be specifically set according to the clarity of the microscopic image. When the clarity is greater, the cancer cell data will be more diverse. At this time, the similarity threshold can be set at about 0.8-0.9 to achieve better distinction. When the clarity is smaller, the data diversity is less, and the value of the cancer cell data is less accurate. Therefore, it is necessary to make the similarity threshold smaller, generally about 0.5-0.7, to avoid the cancer cell number cannot be matched; If so, the cancer cell number of the cancer cell data in the history with the largest similarity value is extracted and marked as the candidate number for the current cancer cell data, and then the next step is entered; If not, it means that the cancer cells corresponding to the cancer cell data may be newly proliferated, and the process goes to step S43 for determination; S42, determining whether a cancer cell number that is the same as the candidate number of the current cancer cell data appears at the previous moment; If yes, the candidate number is used as the cancer cell number of the current cancer cell data, which means that the current cancer cell has not been blocked at the previous moment, and then the process goes to step S5; If not, it means that the current cancer cell was blocked at the previous moment, and the next step is entered; S43, determining whether the cancer cell border of the current cancer cell data has an intersection with other cancer cell data, that is, whether the boundary line of the current cancer cell to be determined has an intersection with the boundary lines of other cancer cells at the current moment, such as Figure 2 As shown, there are intersections between the boundary lines of multiple cancer cells; If yes, the cancer cell data is marked as cancer cell data to be classified, and no cancer cell number is assigned to the cancer cell data. At this time, since the cancer cell corresponding to the cancer cell data is blocked at the previous moment and reappears at the current moment, and the cancer cell is also in contact with and squeezed by other cancer cells, it is unclear whether it is a newly proliferated cancer cell or a previously existing cancer cell. It is necessary to continue to observe and judge in the future, and then enter step S5; If not, proceed to the next step; S44, determining whether the similarity value between the current cancer cell data and the historical cancer cell data is greater than a similarity threshold; If yes, then the cancer cell number of the cancer cell data in the history with the largest similarity value is extracted and marked as the candidate number of the current cancer cell data, thereby completing the re-tracking of the obscured cancer cell when it appears after being obscured, and then proceeding to the next step; If not, a new cancer cell number is assigned to the cancer cell data at the current moment, indicating that the cancer cell is newly proliferated, and then the next step is entered; S45, starting from the current moment, sequentially calculating the similarity values ​​of the rectangular boxes of cancer cells corresponding to the cancer cell data at each moment and the cancer cell data to be classified at the previous moment; S46, determining whether the similarity value is greater than a similarity threshold; If yes, then extract the cancer cell number of the cancer cell data with the largest similarity value, and assign it to the corresponding cancer cell data to be classified at the previous moment, and then proceed to the next step; If not, proceed to the next step.

[0032] In addition, to facilitate subsequent counting, it is best to make the cancer cell number a positive integer, and each time a new cancer cell number is assigned to the cancer cell data at the current moment, the new cancer cell number is 1 greater than the cancer cell number with the largest value that has been generated. In this way, based on the changes in the value of the cancer cell number, it is possible to know how many cancer cells have been newly proliferated and how many cancer cells have died, and based on the cancer cell number of the cancer cell, the change pattern of the cancer cell volume can be known.

[0033] S5. Output monitoring data according to cancer cell data, cancer cell numbers and preset statistical rules, such as counting the number of dead cancer cells, the number of newly proliferated cancer cells and the law of volume changes of cancer cells.

[0034] The present invention also provides a monitoring system for the Chinese medicine inhibition of the proliferation of cervical cancer cells, comprising a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, a monitoring method for the Chinese medicine inhibition of the proliferation of cervical cancer cells is implemented.

[0035] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, so the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0036] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the above embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0037] The above implementation methods have been described in detail. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for monitoring the proliferation of cervical cancer cells by inhibiting the growth of cervical cancer cells with traditional Chinese medicine, comprising a flat micro-culture device for culturing cervical cancer cells, characterized in that: The detection method specifically comprises the following steps: S1, acquiring a microscopic image of the cancer cells in a direction perpendicular to the flat surface of the micro-culture device, and pre-processing the microscopic image to identify the cancer cells; S2, determining whether the current moment is the first moment of the microscopic image; If yes, then the cancer cell data of each cancer cell is obtained, and different numbers are assigned to each cancer cell to obtain the cancer cell number and then the process ends; If not, proceed to step S3; S3, obtaining cancer cell data of each cancer cell at any time, and calculating the similarity between the cancer cell data at the current time and the cancer cell rectangular frame of each cancer cell data in history; S4, setting a similarity threshold, and determining whether the similarity value is greater than the similarity threshold; If so, extract the cancer cell number of the cancer cell data in the history with the largest similarity value, and assign it to the cancer cell data at the current moment; If not, a new cancer cell number is assigned to the cancer cell data at the current moment; S5. Output monitoring data according to cancer cell data, cancer cell numbers and preset statistical rules.

2. The monitoring method according to claim 1, characterized in that: In step S2, the specific steps of acquiring cancer cell data are as follows: S21, establishing an initial rectangular frame for each cancer cell according to a target detection algorithm, and obtaining a cancer cell boundary line; S22, select any edge of the rectangular box and mark it as an active edge, and mark the remaining edges as passive edges; S23, making the active edge tangent to the cancer cell boundary line and obtaining the tangent point, making the passive edge intersect with the cancer cell boundary line and having only one intersection point; S24, moving the cutting point along the cancer cell boundary line, and obtaining a rectangular frame with the smallest area and only one intersection between the active edge and the cancer cell boundary line, and marking it as the cancer cell rectangular frame; S25, sequentially obtaining two mutually perpendicular sides of each edge of the cancer cell rectangular frame, and a first intersection point between the two perpendicular sides and the cancer cell boundary line; S26, obtaining the length of the cancer cell boundary line closest to the frame edge between the two first intersection points, and using it as the virtual length of the frame edge; S27. According to the frame size, angle, position and virtual length of each frame edge of the cancer cell rectangular frame, construct an expression of the cancer cell rectangular frame to obtain cancer cell data; the expression of the cancer cell rectangular frame is as follows: ； In the above formula, and The first and second markers represent the rectangular frame of the cancer cell, respectively. and Respectively represent the horizontal and vertical coordinates of the center point of the cancer cell rectangle. and Respectively represent the width and length of the cancer cell rectangle, where Corresponding to the longest side of the cancer cell rectangular box, S is the data set of the virtual length of the cancer cell boundary line corresponding to each box edge, Indicates the minimum angle that the X-axis passes when it is rotated to be parallel to the edge corresponding to any data in the data set. .

3. The monitoring method according to claim 2, characterized in that: In step S24, the following steps are specifically included: S241, randomly setting a number of sampling points on the cancer cell boundary line, and moving the cutting point along the boundary line for one circle to obtain a number of first rectangular frames when the cutting point is located at the sampling point; S242, selecting a first rectangular frame where the active edge and the cancer cell boundary have two or more intersection points, and marking it as a second rectangular frame; S243, rotating the active edge of the second rectangular frame, and determining whether a rectangular frame having only one intersection point between the active edge and the cancer cell boundary line can be obtained; If yes, rotate the active edge of the second rectangular frame to obtain a new rectangular frame with the smallest area, and mark it as the first rectangular frame; If not, the second rectangular frame and the corresponding sampling points are removed; S244, selecting a first rectangular box with the smallest area and having only one intersection point between the active edge and the cancer cell boundary line, and calculating the absolute value of the area difference between the first rectangular box and the first rectangular box obtained last time; S245, determining whether the absolute value of the area difference is less than the area difference threshold; If yes, the current first rectangular frame is marked as a cancer cell rectangular frame, and then the process goes to step S25; If not, proceed to the next step; S246, selecting a sampling point corresponding to the first rectangular frame with the smallest area, and marking two sampling points adjacent to the sampling point as segmentation points; S247, setting a number of sampling points again between the two segmentation points, and moving the cutting point along the cancer cell boundary line between the two segmentation points, and then returning to step S242.

4. The monitoring method according to claim 3, characterized in that: In step S245, the area difference threshold is 1.0% of the area of ​​the first rectangular frame with the smallest area obtained last time.

5. The monitoring method according to claim 3, characterized in that: In step S241, the steps of setting the sampling points are: S2411, randomly setting a number of initial sampling points on the cancer cell boundary line; S2412, obtaining each convex hull on the cancer cell boundary line; S2413, calculating the ratio of the depth to the arc length of each convex hull in sequence; S2414, setting a depth-to-length ratio threshold, and eliminating convex hulls whose depth-to-arc length ratio is less than the depth-to-length ratio threshold, to obtain a standard convex hull; S2415. Set sampling points at the vertices, starting point, and end point of the standard convex hull.

6. The monitoring method according to claim 5, characterized in that: The number of the initial sampling points is greater than or equal to 12.

7. The monitoring method according to claim 1, characterized in that: In step S3, the following steps are specifically included: S31, rotating the angles of the cancer cell rectangular frames of each cancer cell data at the current moment and in the history to the same angle with the center point as the center, and the angle is a multiple of 90°; S32, calculating the IOU value of the cancer cell rectangular frame corresponding to the converted cancer cell data at the current moment and each cancer cell data in the history; the calculation formula of the IOU value is: ； In the above formula, A and B represent the cancer cell rectangular frame corresponding to the cancer cell data at the current moment and any cancer cell data in the history, respectively. and They represent the horizontal and vertical coordinates of the center point of the cancer cell rectangle A, respectively. and Respectively represent the width and length of the cancer cell rectangle A, and They represent the horizontal and vertical coordinates of the center point of the cancer cell rectangle B, and represent the width and length of object B respectively, and Respectively represent the horizontal and vertical overlap between the cancer cell rectangle A and the cancer cell rectangle B, represents the overlapping area of ​​cancer cell rectangular box A and cancer cell rectangular box B, and Respectively represent the area of ​​cancer cell rectangular box A and cancer cell rectangular box B, Represents the IOU value of cancer cell rectangular box A and cancer cell rectangular box B; S33, calculating the similarity between the cancer cell data at the current moment and any cancer cell data in the history according to the IOU value and the cancer cell data; the similarity calculation formula is: ； In the above formula, Indicates similarity, and denote the first coefficient and the second coefficient respectively, Represents the standard deviation of the difference between the data in the data set of the virtual length in the cancer cell rectangular box A and the corresponding data in the data set of the virtual length in the cancer cell rectangular box B.

8. The monitoring method according to claim 1, characterized in that: In step S4, the following steps are specifically included: S41, setting a similarity threshold, and determining whether the similarity value is greater than the similarity threshold; If so, the cancer cell number of the cancer cell data in the history with the largest similarity value is extracted and marked as the candidate number for the current cancer cell data, and then the next step is entered; If not, proceed to step S43; S42, determining whether a cancer cell number that is the same as the candidate number of the current cancer cell data appears at the previous moment; If yes, the candidate number is used as the cancer cell number of the current cancer cell data, and then the process goes to step S5; If not, proceed to the next step; S43, determining whether the cancer cell border of the current cancer cell data has an intersection with other cancer cell data; If yes, the cancer cell data is marked as cancer cell data to be classified, and no cancer cell number is assigned to the cancer cell data, and then the process goes to step S5; If not, proceed to the next step; S44, determining whether the similarity value between the current cancer cell data and the historical cancer cell data is greater than a similarity threshold; If so, the cancer cell number of the cancer cell data in the history with the largest similarity value is extracted and marked as the candidate number for the current cancer cell data, and then the next step is entered; If not, a new cancer cell number is assigned to the cancer cell data at the current moment, and then the next step is entered; S45, starting from the current moment, sequentially calculating the similarity values ​​of the cancer cell rectangular frames corresponding to the cancer cell data at each moment and the cancer cell data to be classified at the previous moment; S46, determining whether the similarity value is greater than a similarity threshold; If yes, then extract the cancer cell number of the cancer cell data with the largest similarity value, and assign it to the corresponding cancer cell data to be classified at the previous moment, and then proceed to the next step; If not, proceed to the next step.

9. The monitoring method according to claim 8, characterized in that: The cancer cell number is a positive integer, and each time a new cancer cell number is assigned to the cancer cell data at the current moment, the new cancer cell number is 1 greater than the maximum cancer cell number that has been generated.

10. A system for implementing the monitoring method of the Chinese medicine for inhibiting the proliferation of cervical cancer cells according to any one of claims 1 to 9, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the method for monitoring the proliferation status of cervical cancer cells inhibited by traditional Chinese medicine according to any one of claims 1 to 9 is implemented.

Images