A method and system for evaluating a coronary artery shunt plug based on image segmentation

Abstract

The present application relates to the technical field of medical instrument evaluation, and provides a coronary artery shunt thrombus evaluation method and system based on image segmentation, comprising: acquiring follow-up data of an experimental group and a control group collected by a data acquisition device before and after surgery; acquiring an instrument blood vessel surface image of the experimental group or the control group after the use of the instrument is completed, obtaining a plurality of thrombus regions through an image segmentation model; for each thrombus region, calculating color moments on different color channels, and calculating the mean value of the color moments of all color channels to determine whether it is within a set range, and if so, the thrombus region is retained; judging the thrombus formation grade based on the position, number and area of the thrombus region; for the follow-up data and the thrombus formation grade, comparing the experimental group and the control group to determine whether the test instrument can achieve the use effect of the control instrument. The coronary artery shunt thrombus evaluation is standardized and automated, and the coronary artery shunt thrombus evaluation accuracy is improved.

Description

Technical Field

[0001] This invention belongs to the field of medical device evaluation technology, and in particular relates to a method and system for evaluating coronary artery shunt thrombi based on image segmentation. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] A coronary shunt embolization (CSE) is a device used in cardiovascular surgery, primarily to treat coronary artery disease. The coronary arteries are the main blood vessels supplying the heart; when they narrow or become blocked, it can lead to myocardial ischemia and even myocardial infarction. The main function of a CSE is to improve blood supply to the myocardium by creating a shunt between the coronary artery and other blood vessels. The use of a CSE usually requires surgical intervention. During the procedure, the surgeon inserts the CSE into the narrowed or blocked area of ​​the coronary artery. The CSE is designed so that blood can bypass the narrowed or blocked coronary artery and supply the myocardium through its internal cavity. This effectively restores blood supply to the myocardium, alleviates symptoms of myocardial ischemia, and reduces the risk of myocardial infarction. CSEs are typically made of flexible materials to adapt to the shape and curvature of the coronary arteries. They are generally biocompatible and can remain in the body for extended periods without causing adverse reactions. The size and shape of the CSE can be selected based on the patient's specific situation to ensure optimal treatment outcomes. CSEs play an important role in neuro- and cardiovascular surgeries. They can help improve blood supply to the heart muscle, alleviate symptoms of myocardial ischemia, and reduce the risk of myocardial infarction.

[0004] Medical devices exempt from clinical trials are those that can obtain medical device registration certificates through comparison with similar medical devices. Coronary artery shunt thrombi are among the devices that can be compared with similar products. The comparison method involves selecting medical devices that are as similar as possible to the tested device in terms of their scope of application, applicable site, structural design, and materials for comparative verification. Typically, any differences between devices need to be verified in vivo on animals, and the acceptability of these differences must be evaluated.

[0005] Currently, there is no unified standard method for animal experiments comparing the differences in coronary artery shunt thrombi, including the selection of animals, observation period, observation indicators, and observation methods. Moreover, the comparison between the test device and the control device relies on human observation, which has a large error margin. Furthermore, it requires staff to be very familiar with the evaluation criteria, which places high demands on the staff. In addition, it is difficult to trace the experimental process. Summary of the Invention

[0006] To address the technical problems mentioned above, this invention provides a method and system for evaluating coronary artery shunt thrombi based on image segmentation. By comparing and standardizing experimental procedures and image acquisition and processing, the method achieves standardization and automation of coronary artery shunt thrombi evaluation. Furthermore, during thrombus segmentation, the method filters thrombus regions based on color moments, removing bloodstains that are incorrectly segmented as thrombus regions, thus improving the accuracy of thrombus region segmentation and consequently enhancing the accuracy of coronary artery shunt thrombi evaluation.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] The first aspect of the present invention provides a method for evaluating coronary artery shunt thrombi based on image segmentation, comprising:

[0009] Obtain preoperative images of several test devices and control devices, compare them with standard images, and determine whether the device models are correct. If the models are correct, assign all test devices to the experimental group and all control devices to the control group.

[0010] Before and after the operation, follow-up data of the experimental and control groups were acquired by the data acquisition device.

[0011] After the device is used, images of the blood vessel surface of the experimental group or control group are acquired. Several thrombus regions are obtained through image segmentation model. For each thrombus region, the color moments on different color channels are calculated, and the mean of the color moments of all color channels is calculated. It is determined whether the mean is within the set range. If it is, the thrombus region is retained; otherwise, the thrombus region is deleted. The thrombus formation level is determined based on the location, number, and area of ​​the thrombus regions.

[0012] The follow-up data and thrombosis levels were compared between the experimental group and the control group to determine whether the tested device could achieve the same effect as the control device.

[0013] Furthermore, before comparing the experimental group and the control group, it is determined whether the follow-up data and thrombosis grade of the experimental group or the control group are statistically significant.

[0014] Furthermore, if the specifications of the tested device are within the set range, the follow-up data include myocardial marker data, blood indicators, and imaging indicators at different times before and after the operation. The myocardial marker data is collected by a cardiac marker detector, the blood indicators are collected by a fully automated flow cytometer and biochemical analyzer, and the imaging indicators are collected by computed tomography and angiography equipment.

[0015] Furthermore, if the specifications of the tested device are smaller than the set range, the follow-up data include the immediate bleeding volume and average blood flow within a certain period of time after the blood vessel is severed.

[0016] Furthermore, if the specifications of the tested device are smaller or larger than the set range, the follow-up data include the mean arterial pressure at the proximal and distal ends of the target vessel at different times after the device is inserted into the target vessel.

[0017] Furthermore, if the specifications of the test instrument are smaller or larger than the set range, the comparison between the experimental group and the control group is also based on the classification of endometrial damage and internal elastic membrane damage in histopathology.

[0018] Furthermore, if the specifications of the tested device are smaller or larger than the set range, the comparison between the experimental group and the control group is also based on whether there is endothelial damage to the blood vessels of the device.

[0019] A second aspect of the present invention provides a coronary shunt thrombus evaluation system based on image segmentation, comprising:

[0020] The device grouping module is configured to: acquire preoperative images of several test devices and control devices, compare them with standard images, determine whether the device model is correct, and if the model is correct, assign all test devices to the experimental group and all control devices to the control group.

[0021] The follow-up data acquisition module is configured to acquire follow-up data of the experimental and control groups collected by the data acquisition device before and after surgery.

[0022] The thrombosis grading module is configured to: after the instrument is used, acquire images of the blood vessel surface of the experimental or control group, obtain several thrombosis regions through an image segmentation model; for each thrombosis region, calculate the color moments on different color channels, calculate the mean of the color moments of all color channels, determine whether the mean is within a set range, if so, retain the thrombosis region, otherwise delete the thrombosis region; and determine the thrombosis grading level based on the location, number, and area of ​​the thrombosis regions.

[0023] The comparison module is configured to: for the follow-up data and thrombosis level, determine whether the test device can achieve the same effect as the control device by comparing the experimental group and the control group.

[0024] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the image segmentation-based coronary shunt thrombus evaluation method described above.

[0025] A fourth aspect of the present invention provides a computer device including a computer-readable storage medium, a processor, and a computer program stored on the computer-readable storage medium and executable on the processor, wherein the processor executes the program to implement the steps of the image segmentation-based coronary shunt thrombus evaluation method described above.

[0026] Compared with the prior art, the beneficial effects of the present invention are:

[0027] This invention achieves standardization and automation of coronary artery shunt thrombus evaluation by comparing experimental procedures and image acquisition and processing. Furthermore, during thrombus segmentation, the thrombus region is screened based on color moments, which can remove bloodstains that are incorrectly segmented as thrombus regions, thereby improving the accuracy of thrombus region segmentation and thus improving the accuracy of coronary artery shunt thrombus evaluation.

[0028] This invention achieves a comparison between experimental and control instruments by real-time recording of preoperative, intraoperative, and postoperative test data, followed by standardized comparison and statistical analysis.

[0029] This invention standardizes the comparative testing process, ensures the authenticity of the instruments used, and solves the problem of the inability to standardize the comparison of differences between instruments from different brands.

[0030] This invention helps experimental devices obtain standardized comparison results with the same species more quickly. By inputting animal test data, a final conclusion can be drawn as to whether the differences between the devices are acceptable, which can greatly accelerate the medical device registration process. Attached Figure Description

[0031] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0032] Figure 1 This is a flowchart of a coronary artery shunt thrombus evaluation method based on image segmentation according to Embodiment 1 of the present invention;

[0033] Figure 2 This is a first schematic diagram of a coronary artery shunt thrombus evaluation method based on image segmentation according to Embodiment 1 of the present invention configured on a computer.

[0034] Figure 3 This is a second schematic diagram of a coronary artery shunt thrombus evaluation method based on image segmentation according to Embodiment 1 of the present invention, configured on a computer.

[0035] Figure 4 This is a third schematic diagram of a method for evaluating coronary artery shunt thrombi based on image segmentation according to Embodiment 1 of the present invention, configured on a computer.

[0036] Figure 5 This is a schematic photograph of the outer surface of the instrument according to Embodiment 1 of the present invention;

[0037] Figure 6 This is a schematic diagram of the experimental method shown in Embodiment 1 of the present invention;

[0038] Figure 7 This is an experimental schematic diagram of Embodiment 1 of the present invention;

[0039] Figure 8 This is a schematic diagram of the structure of a computer device according to Embodiment 4 of the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0041] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0042] Example 1

[0043] This embodiment provides a method for evaluating coronary artery shunt thrombi based on image segmentation.

[0044] This embodiment provides a method for evaluating coronary artery shunt thrombi based on image segmentation. Application scenario: Animal testing center. Preoperatively, a camera system collects overall images of the instruments in the experimental and control groups, which are then entered into the system for storage and identification. At the start of the surgery, the system monitors and records in real time to confirm that the instruments in both groups are used according to the protocol. If the use deviates from the protocol, the system will issue an alarm. Data throughout the animal testing process (including preoperative, intraoperative, and postoperative data) is collected according to the animal testing protocol and entered according to time nodes. Finally, statistical analysis (using a control test) is conducted to compare the experimental and control instruments (one or more instruments can be compared to output a final conclusion). In vivo testing may include: comparison of commonly used specifications and models; large animal in situ cardiac testing (performed under cardiopulmonary bypass and non-cardiopulmonary bypass conditions); and comparison of extreme specifications and models (using the carotid and celiac arteries of small animals).

[0045] This embodiment provides a method for evaluating coronary artery shunt thrombi based on image segmentation, such as... Figure 1 As shown, it includes the following steps:

[0046] Step 1: Staff enter the model number of the coronary artery shunt thrombus (test device) to be evaluated, classify the devices based on the model number, and divide them into standard usage specifications and extreme specifications according to the stored settings; enter the model number of the control device and associate it with the test device; enter and store photos of the test device and control device as standard photos.

[0047] Step 2: Display the experimental method based on the model category.

[0048] For standard-use models (with the test device specifications within the set range), the experimental method is as follows: orthotopic cardiac testing using large animals (such as experimental pigs), with procedures involving both cardiopulmonary bypass and non-cardiopulmonary bypass.

[0049] A. Surgical procedure without cardiopulmonary bypass: Systemic heparinization, with the heart not stopping, the left anterior descending branch / circular branch is cut open, a standard type shunt embolism (experimental device or control device) is placed, the electrocardiogram is recorded, the device is removed after the operation, the blood vessel is anastomosed, and the patient is continuously observed for 7 days.

[0050] B. Surgical procedure under cardiopulmonary bypass: Establish cardiopulmonary bypass with full heparinization. After cardiac arrest, cut open the left anterior descending branch / circular branch and place a standard-sized shunt embolism (experimental device or control device). Remove the device postoperatively, anastomose the blood vessels, and observe for 7 days.

[0051] For extreme specification models, the experimental method shown is as follows: Figure 6 As shown, the surgical procedure was performed using small animal (such as laboratory rabbit) vascular experiments:

[0052] A. Comparison of the smallest size instrument: After heparinization of the animal, the common carotid artery was exposed, and the diameter of the vessel was measured using calipers; one side of the common carotid artery was clamped, and an incision was made in the other side of the common carotid artery, and a small size test instrument (or control instrument) was inserted. After insertion, the blood pressure was measured at both the proximal and distal ends of the vessel and the blood pressure values ​​were recorded; shortly afterward, the distal end of the inserted test instrument (or control instrument) was detached, and the total amount of bleeding through the test instrument (or control instrument) within a certain period of time after detachment was collected, the flow rate was calculated, and the test instrument (or control instrument) was removed after completion;

[0053] B. Comparison with the largest size instrument: After heparinization of the animal, the abdominal aorta was exposed, the diameter of the vessel was measured using a vernier caliper, the largest size test instrument (or control instrument) was inserted, and the pressure was measured at both the proximal and distal ends of the vessel. The blood pressure values ​​were recorded, and the test instrument (or control instrument) was removed after completion.

[0054] Step 3: Enter preoperative laboratory and imaging data and associate them with the test device; take several equal numbers of test devices and control devices, take preoperative photos of the test devices and control devices, and compare them with the standard photos of the test devices and control devices stored in Step 1 to confirm the device model. If all test devices and control devices are of the correct model, group all test devices and control devices as one device, assign the test devices to the experimental group, and assign the control devices to the control group; perform the operation according to the displayed experimental method, such as... Figure 7 As shown.

[0055] Step 4: Before and after the operation, use data acquisition equipment to collect and store laboratory data (also known as follow-up data), and determine whether the collected laboratory data is statistically significant.

[0056] For standard usage specifications, follow-up data should include at least myocardial marker data (troponin, myoglobin, and creatine kinase isoenzyme test results), blood parameters (blood biochemistry test results), and imaging parameters (distal diameter of the target vessel), specifically:

[0057] (1) Analysis of myocardial markers: After centrifugation of venous blood, serum was collected and placed in a cardiac marker detector. The results of troponin, myoglobin, creatine kinase isoenzyme, etc., were automatically entered into the system before the operation and 24 hours, 72 hours and 7 days after the operation. The results were expressed as mean ± standard deviation and independent samples t test was used. P < 0.05 was considered statistically significant.

[0058] (2) Blood index analysis: After centrifugation, venous blood was collected and serum was obtained. The serum was then tested using an automated flow cytometer and biochemical analyzer. Blood routine and blood biochemical test results were displayed before surgery, 24 hours after surgery, 72 hours after surgery, and 7 days after surgery. The results were automatically entered into the system and expressed as mean ± standard deviation. The data were analyzed in the system and analyzed using an independent samples t-test. P < 0.05 was considered statistically significant.

[0059] (3) Imaging index analysis: Preoperative, immediate postoperative and 7-day vascular data were entered into the system using computed tomography and angiography equipment. The main data was the distal diameter of the target vessel, expressed as mean ± standard deviation. The data were entered into the system for analysis, and the independent samples t test was used. P < 0.05 was considered statistically significant.

[0060] For the most extreme specifications, follow-up data must include at least blood pressure and / or blood flow, specifically:

[0061] (1) Blood flow analysis: After using the smallest size test device (control device), the blood vessel was cut off and the amount of bleeding was recorded within a certain period of time. The mean ± standard deviation of the instantaneous bleeding volume and the average blood flow were calculated and entered into the system for analysis. The independent samples t test was used, and P < 0.05 was considered statistically significant.

[0062] (2) Blood pressure analysis: After the test device (control device) was used on the target vessel, the pressure at the proximal and distal ends of the target vessel was measured simultaneously. The mean arterial pressure at the proximal and distal ends of the target vessel was recorded at regular intervals. The data were recorded and the mean pressure at the distal end of the target vessel was analyzed. The mean pressure immediately after device placement and the mean arterial pressure at the start and end time points were compared and analyzed between the experimental group and the control group. The results of vessel diameter, mean arterial pressure difference at the start and end time points and immediately after placement were expressed as mean ± standard deviation. The data were entered into the system for analysis. The independent samples t test was used. P < 0.05 was considered statistically significant.

[0063] Step 4: After the instrument is used, acquire the surface image data of the blood vessels in the experimental group or control group, such as... Figure 5 As shown, several thrombus regions are obtained through the image segmentation model. For each thrombus region obtained by the image segmentation model, the second-order color moments (i.e., standard deviations) on the three RGB channels are calculated, and the mean of the three second-order color moments is calculated. It is determined whether the mean of the second-order color moments is within the set range. If it is, the thrombus region is retained; otherwise, the thrombus region is deleted. Based on the location, number, and area of ​​the thrombus regions, the thrombus formation level is determined, and it is determined whether the obtained thrombus formation level is statistically significant.

[0064] For standard specifications and models, the system identifies the test device or control device, takes photos of the outer surface of the device, and compares and confirms the thrombus formation on the surface of the test device (control device) after it is removed from the blood vessel. The results of the test group and the control group are expressed as mean ± standard deviation, entered into the system for analysis, and an independent samples t-test is used. P < 0.05 is considered statistically significant.

[0065] For extreme specifications, record the presence or absence of endothelial damage in the blood vessels of the test device (control device) and the presence of thrombus formation on the sample surface after removal of the test device (control device). Results from the experimental and control groups are expressed as mean ± standard deviation, entered into the system for analysis, and analyzed using an independent samples t-test. P < 0.05 was considered statistically significant.

[0066] The presence or absence of endothelial damage in the blood vessels of the test device (control device) was determined by an image recognition model, which employed a convolutional neural network to identify the location of the endothelial damage.

[0067] The image segmentation model used is Mask R-CNN.

[0068] In this embodiment, to avoid the influence of bloodstains on the image segmentation model, for each thrombus region obtained by the image segmentation model, the second-order color moments (i.e., standard deviations) on the three RGB channels are calculated, and the mean of the three second-order color moments is calculated. It is then determined whether the mean of the second-order color moments is within a set range. If it is, the thrombus region is retained; otherwise, it is deleted. This is because thrombi have richer color variations than bloodstains, and this method can remove bloodstains that have been incorrectly segmented as thrombus regions.

[0069] In this embodiment, the determination of the thrombosis grade is based on the thrombosis classification of medical devices in GB / T16886.4—2022, as shown in Table 1.

[0070] Table 1. Classification Basis

[0071] Thrombosis grade Observation of thrombosis 0 No thrombosis (small blood clots may be present at the sample insertion site). 1 Very minor thrombosis, such as a single blood clot or a very thin blood clot in the sample. 2 Minor thrombosis, such as the presence of very small blood clots in multiple locations on the sample. 3 Moderate thrombosis, such as when the blood clot covers less than 1 / 2 of the length of the implanted sample. 4 Severe thrombosis, such as a blood clot covering more than 1 / 2 of the length of the implanted sample. 5 Vascular occlusion after sample removal

[0072] In this embodiment, if the number of thrombus regions is less than a first threshold and the sum of the areas of all thrombus regions is less than a first set value, and the location of the thrombus region is at the insertion port, then the thrombosis level is 0; if the number of thrombus regions is less than the first threshold and the sum of the areas of all thrombus regions is less than the first set value, and the location of the thrombus region is not at the insertion port, then the thrombosis level is 1; if the number of thrombus regions is greater than the first threshold and the sum of the areas of all thrombus regions is greater than the first set value but less than the second set value, then the thrombosis level is 2; if the sum of the areas of all thrombus regions is greater than the second set value but less than the third set value, then the thrombosis level is 3; if the sum of the areas of all thrombus regions is greater than the third set value, then the thrombosis level is 4.

[0073] In this embodiment, if the staff finds vascular occlusion after taking out the sample, the thrombosis level is directly recorded as level 5, and image segmentation is no longer performed.

[0074] Step 5: Obtain microscopic images of the tissue pathology. Using an image segmentation model, obtain the target vessel intima and internal elastic lamina. For the target vessel intima and internal elastic lamina, use an image classification model to obtain intima damage classification and internal elastic lamina damage classification.

[0075] This step applies only to extreme specification models.

[0076] Histopathological analysis and microscopic observation were performed, during which the system automatically identified the intima and internal elastic lamina of the target blood vessel within the marked area. An image classification model was used to classify intimal and internal elastic lamina injuries. Results from the experimental and control groups were statistically analyzed, expressed as mean ± standard deviation. The results were entered into the system for analysis, and an independent samples t-test was used. P < 0.05 was considered statistically significant.

[0077] In this embodiment, the training set used by the image classification model during training is obtained by expert calibration. The basis for the classification of endometrial injury and internal elastic membrane injury during the expert calibration process is shown in Tables 2 and 3.

[0078] Table 2. Criteria for Classification of Intimal Injuries

[0079]

[0080]

[0081] Table 3. Basis for classifying internal elastic membrane damage

[0082] Damage classification Pathological observation 0 The internal elastic membrane is intact. 1 Focal injury of internal elastic membrane 2 Internal elastic membrane damage and rupture 3 Most of the internal elastic membrane was damaged and ruptured.

[0083] Step 6: After preoperative data, image data, and pathological data are collected, they will be automatically entered into the corresponding grouped instrument data table. The system will then automatically begin verification according to the protocol requirements, ensuring all data meet the following standards:

[0084] A. The thrombus grading on the surface of the tested instrument sample was significantly different from that of the control instrument (P > 0.05).

[0085] B. Compared with the control device, the cardiac markers of the tested device were significantly different (P > 0.05).

[0086] C. Compared with the control device, the imaging data of the tested device showed P > 0.05;

[0087] D. The presence or absence of endothelial damage in the blood vessels of the tested device compared to the control device was P > 0.05;

[0088] E. Compared with the control device, the smallest size test device showed significantly different results in terms of bleeding volume and mean blood flow (P > 0.05).

[0089] F. Compared with the control device, the mean distal arterial pressure difference of the smallest size test device was P > 0.05;

[0090] G. The pathological results of the vascular intima and internal elastic membrane of the largest-sized test device were compared with those of the control device, P>0.05.

[0091] If, after comparing all AG data, the P-value is greater than 0.05, the system outputs that there is no difference in use between the test device and the control device. Whether the test device can achieve the same effect as the control device is considered a successful comparison result, and the test device can be considered suitable for human use. If, after comparing all AG data, one or more P-values ​​are less than 0.05, the system outputs that there is a difference in use between the test device and the control device. The cause needs to be analyzed, and targeted improvements to the test device should be recommended.

[0092] In this embodiment, in vivo animal control verification is carried out under system supervision. The control device is a device that has obtained a medical device registration certificate in China or has obtained a medical device registration certificate overseas, but there is currently no similar device in China. The test device is a device that has not yet obtained domestic or overseas registration, but is required to undergo animal test verification according to regulations.

[0093] This embodiment provides a coronary artery shunt thrombus evaluation method based on image segmentation, which can be configured on a computer or a mobile device, such as... Figure 2 , Figure 3 and Figure 4 The image shows the result configured on the computer.

[0094] This embodiment provides a method for evaluating coronary artery shunt thrombi based on image segmentation. By real-time recording of preoperative, intraoperative, and postoperative test data, standardized comparison is performed, and statistical analysis is conducted to compare the test device with the control device.

[0095] This embodiment provides a coronary artery shunt thrombus evaluation method based on image segmentation. For data that is difficult to measure directly using equipment, it achieves automated identification through image acquisition and image segmentation technologies, eliminating reliance on human observation.

[0096] This embodiment provides a coronary artery shunt thrombus evaluation method based on image segmentation. During the thrombus segmentation process, the thrombus region is screened based on color moments, which can remove bloodstains that are incorrectly segmented as thrombus regions, improve the segmentation accuracy of thrombus regions, and thus improve the evaluation accuracy of coronary artery shunt thrombi.

[0097] This embodiment provides a method for evaluating coronary artery shunt thrombi based on image segmentation, which standardizes the comparative test process, ensures the authenticity of the devices used, and solves the problem of the inability to standardize the comparison of differences between devices from different brands.

[0098] This embodiment provides a coronary artery shunt thrombus evaluation method based on image segmentation, which can help test devices obtain standardized comparison results with the same species more quickly. By inputting animal test data results, a final conclusion can be drawn on whether the differences between the devices are acceptable, which can greatly accelerate the medical device registration process.

[0099] Example 2

[0100] This embodiment provides a coronary artery shunt thrombus evaluation system based on image segmentation, which specifically includes:

[0101] The device grouping module is configured to: acquire preoperative images of several test devices and control devices, compare them with standard images, determine whether the device model is correct, and if the model is correct, assign all test devices to the experimental group and all control devices to the control group.

[0102] The follow-up data acquisition module is configured to acquire follow-up data of the experimental and control groups collected by the data acquisition device before and after surgery.

[0103] The thrombosis grading module is configured to: after the instrument is used, acquire images of the blood vessel surface of the experimental or control group, obtain several thrombosis regions through an image segmentation model; for each thrombosis region, calculate the color moments on different color channels, calculate the mean of the color moments of all color channels, determine whether the mean is within a set range, if so, retain the thrombosis region, otherwise delete the thrombosis region; and determine the thrombosis grading level based on the location, number, and area of ​​the thrombosis regions.

[0104] The comparison module is configured to: for the follow-up data and thrombosis level, determine whether the test device can achieve the same effect as the control device by comparing the experimental group and the control group.

[0105] It should be noted that each module in this embodiment corresponds one-to-one with each step in Embodiment 1, and their specific implementation processes are the same, so they will not be repeated here.

[0106] Example 3

[0107] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the image segmentation-based coronary shunt thrombus evaluation method described in Embodiment 1 above.

[0108] Example 4

[0109] This embodiment provides a computer device, such as... Figure 8 As shown, the system includes a computer-readable storage medium 1003, a processor 1001, a communication interface 1002, and a computer program stored on the computer-readable storage medium 1003 and executable on the processor 1001. The processor 1001, communication interface 1002, and computer-readable storage medium 1003 can be connected via a bus or other means. The communication interface 1002 is used to receive and send data. When the processor 1001 executes the program, it implements the steps in the image segmentation-based coronary artery shunt thrombus evaluation method described in Embodiment 1 above.

[0110] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0111] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0112] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0113] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for evaluating coronary artery shunt thrombi based on image segmentation, characterized in that, include: Obtain preoperative images of several test devices and control devices, compare them with standard images, and determine whether the device models are correct. If the models are correct, assign all test devices to the experimental group and all control devices to the control group. Before and after the operation, follow-up data of the experimental and control groups were acquired by the data acquisition device. After the device is used, images of the blood vessel surface of the experimental group or control group are acquired. Several thrombus regions are obtained through image segmentation model. For each thrombus region, the color moments on different color channels are calculated, and the mean of the color moments of all color channels is calculated. It is determined whether the mean is within the set range. If it is, the thrombus region is retained; otherwise, the thrombus region is deleted. The thrombus formation level is determined based on the location, number, and area of ​​the thrombus regions. For the follow-up data and thrombosis grade, the experimental group and the control group are compared to determine whether the test device can achieve the effect of the control device. If the specifications of the test device are within the set range, the follow-up data include myocardial marker data, blood indicators and imaging indicators at different times before and after the operation. If the specifications of the tested device are smaller or larger than the set range, the comparison between the experimental group and the control group is also based on the classification of intimal injury and internal elastic membrane injury in histopathology, and the comparison between the experimental group and the control group is also based on whether there is endothelial injury in the blood vessels of the device.

2. The method for evaluating coronary artery shunt thrombi based on image segmentation as described in claim 1, characterized in that, Before comparing the experimental group and the control group, it was determined whether the follow-up data and thrombosis grade of the experimental group or the control group were statistically significant.

3. The method for evaluating coronary artery shunt thrombi based on image segmentation as described in claim 1, characterized in that, The myocardial biomarker data were collected by a cardiac biomarker detector, the blood indicators were collected by a fully automated flow cytometer and biochemical analyzer, and the imaging indicators were collected by computed tomography and angiography equipment.

4. The method for evaluating coronary artery shunt thrombi based on image segmentation as described in claim 1, characterized in that, If the specifications of the tested device are smaller than the set range, the follow-up data include the immediate bleeding volume and average blood flow within a certain period of time after the blood vessel is severed.

5. The method for evaluating coronary artery shunt thrombi based on image segmentation as described in claim 1, characterized in that, If the specifications of the test device are smaller or larger than the set range, the follow-up data include the mean arterial pressure at the proximal and distal ends of the target vessel at different times after the device is inserted into the target vessel.

6. A coronary artery shunt thrombus evaluation system based on image segmentation, characterized in that, include: The device grouping module is configured to: acquire preoperative images of several test devices and control devices, compare them with standard images, determine whether the device model is correct, and if the model is correct, assign all test devices to the experimental group and all control devices to the control group. The follow-up data acquisition module is configured to acquire follow-up data of the experimental and control groups collected by the data acquisition device before and after surgery. The thrombosis grading module is configured to: after the instrument is used, acquire images of the blood vessel surface of the experimental or control group, obtain several thrombosis regions through an image segmentation model; for each thrombosis region, calculate the color moments on different color channels, calculate the mean of the color moments of all color channels, determine whether the mean is within a set range, if so, retain the thrombosis region, otherwise delete the thrombosis region; and determine the thrombosis grading level based on the location, number, and area of ​​the thrombosis regions. The comparison module is configured to: determine whether the test device can achieve the same effect as the control device by comparing the follow-up data and thrombosis level between the experimental group and the control group; if the specifications of the test device are within the set range, the follow-up data include myocardial marker data, blood indicators and imaging indicators at different times before and after the operation. If the specifications of the tested device are smaller or larger than the set range, the comparison between the experimental group and the control group is also based on the classification of intimal injury and internal elastic membrane injury in histopathology, and the comparison between the experimental group and the control group is also based on whether there is endothelial injury in the blood vessels of the device.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the steps in the image segmentation-based coronary shunt thrombus evaluation method as described in any one of claims 1-5.

8. A computer device comprising a computer-readable storage medium, a processor, and a computer program stored on the computer-readable storage medium and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the image segmentation-based coronary shunt thrombus evaluation method as described in any one of claims 1-5.

Images