Coronary angiography image segmentation method, device and system considering main vessel obstruction

Abstract

The present invention provides a method, device and system for segmenting a coronary angiography image taking into account the obstruction of the main vessel. First, a coronary angiography image is acquired; the whole vessel segmentation of the coronary angiography image is performed to obtain a first segmented image; then the coronary angiography image is identified to determine the obstruction information of the main vessel; then the coronary angiography image is segmented according to the obstruction information of the main vessel to obtain a second segmented image; finally, the first segmented image and the second segmented image are feature fused to obtain the segmentation result of the coronary angiography image. The main vessel is usually the most obvious vessel in the image. By segmenting the main vessel separately, different main vessel images are segmented according to obstruction and non-obstruction, i.e., the second segmented image, to avoid combining other vessels with conventional whole vessel segmentation when the main vessel is blocked, thereby avoiding that when the main vessel is blocked, the segmentation model identifies other clear and long vessels as the main vessel, resulting in vessel segmentation errors.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular relates to a method, device and system for segmenting coronary angiography images taking into account main vessel obstruction. Background Art

[0002] Contrast images are a widely used type of medical images. Among them, the acquisition method of cardiovascular contrast images is to insert a catheter through the femoral artery or other peripheral arteries, send it to the ascending aorta, then find the left or right coronary artery orifice and insert it, inject contrast agent, make the coronary artery develop under X-rays, and then take a contrast image. Since other tissues such as bones in the human body are also photographed by X-rays, there is often a lot of noise in the contrast image, and the contrast image is easily blurred, so the contrast image needs to be processed.

[0003] Vascular segmentation technology is the basis of angiographic image processing. In the prior art, angiographic images are usually segmented through machine learning models, and the accuracy of machine learning is affected by data quality. The prediction results of machine learning models depend to a large extent on the quality and representativeness of training data. Different people have different coronary artery conditions, so the data used in conventional machine learning is difficult to represent all coronary artery conditions, resulting in poor angiographic image processing results. Summary of the invention

[0004] In view of this, the present invention provides a method, device and system for segmenting coronary angiography images taking into account main vessel obstruction, aiming to solve the problem of the effect of angiography image processing in the prior art.

[0005] A first aspect of an embodiment of the present invention provides a coronary angiography image segmentation method considering main vessel obstruction, comprising:

[0006] Obtain coronary angiographic images;

[0007] Performing whole-vessel segmentation on the coronary angiography image to obtain a first segmented image;

[0008] Identify coronary angiography images and determine the main blood vessel blockage information;

[0009] Segmenting the coronary angiography image according to the main vessel occlusion information to obtain a second segmented image;

[0010] The first segmented image and the second segmented image are subjected to feature fusion to obtain a coronary angiography image segmentation result.

[0011] A second aspect of an embodiment of the present invention provides a coronary angiography image segmentation device taking into account main vessel obstruction, comprising:

[0012] An image acquisition module, used for acquiring coronary angiography images;

[0013] A whole blood vessel segmentation module, used for performing whole blood vessel segmentation on the coronary angiography image to obtain a first segmented image;

[0014] The blockage identification module is used to identify the coronary angiography image and determine the blockage information of the main blood vessels;

[0015] A main vessel segmentation module, used to segment the coronary angiography image according to the main vessel obstruction information to obtain a second segmented image;

[0016] The feature fusion module is used to perform feature fusion on the first segmented image and the second segmented image to obtain a coronary angiography image segmentation result.

[0017] A third aspect of an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the coronary angiography image segmentation method considering main vessel obstruction as described in the first aspect above are implemented.

[0018] A fourth aspect of an embodiment of the present invention provides an angiography image processing system, comprising a vascular angiography device and the electronic device according to the third aspect above.

[0019] A fifth aspect of an embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the coronary angiography image segmentation method considering main vessel obstruction as described in the first aspect above.

[0020] The coronary angiography image segmentation method, device and system considering the main vessel obstruction provided by the embodiment of the present invention first obtain a coronary angiography image; perform full vessel segmentation on the coronary angiography image to obtain a first segmented image; then identify the coronary angiography image to determine the main vessel obstruction information; then segment the coronary angiography image according to the main vessel obstruction information to obtain a second segmented image; finally, feature fusion is performed on the first segmented image and the second segmented image to obtain the coronary angiography image segmentation result. The main vessel is usually the most obvious vessel in the image. By segmenting the main vessel separately, different main vessel images are segmented according to obstruction and non-obstruction, i.e., the second segmented image, to avoid combining other vessels with conventional full vessel segmentation when the main vessel is blocked, thereby avoiding the segmentation model identifying other clear and long vessels as the main vessel when the main vessel is blocked, resulting in vessel segmentation errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0022] Figure 1 This is a diagram of an application scenario of coronary angiography image segmentation considering main vessel obstruction provided by an embodiment of the present invention;

[0023] Figure 2 is a flow chart for implementing a coronary angiography image segmentation method considering main vessel obstruction provided by an embodiment of the present invention;

[0024] Figure 3 is a schematic diagram of the structure of a coronary angiography image segmentation device taking into account main vessel obstruction provided by an embodiment of the present invention;

[0025] Figure 4 It is a schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0027] Figure 1 : is an application scenario diagram of coronary angiography image segmentation considering main vessel obstruction provided by an embodiment of the present invention. Figure 1 As shown, in some embodiments, the coronary angiography image segmentation considering main vessel obstruction provided by the embodiment of the present invention can be applied to but not limited to this application scenario. The system may include: an angiography device 11 and a processing terminal 12.

[0028] First, the catheter needs to be inserted through the patient's femoral artery or other peripheral artery and sent to the ascending aorta. Then, the left or right coronary artery orifice is found and inserted. Then, contrast agent is injected into the coronary artery. At this time, the angiography device 11 captures the developed angiography image and sends it to the processing terminal 12. The processing terminal 12 segments and processes the angiography image to obtain a clear cardiovascular segmentation map.

[0029] Figure 2 FIG. 4 is a flow chart of the implementation of the coronary angiography image segmentation method considering main vessel obstruction provided by an embodiment of the present invention. Figure 2As shown, the coronary angiography image segmentation method considering the main vessel obstruction includes:

[0030] S210, obtaining a coronary angiography image.

[0031] In an embodiment of the present invention, the initial angiographic image may be Figure 1 The data may be taken in real time by the angiography device in the hospital, or may be obtained from the hospital's information management system, which is not limited here.

[0032] S220, performing whole-vessel segmentation on the coronary angiography image to obtain a first segmented image.

[0033] In some embodiments, S220 includes: inputting the coronary angiography image into the whole vessel segmentation model to obtain a first segmented image. Using the trained model, a batch of unlabeled angiography images are processed, and the prediction results are optimized using a double threshold post-processing method to obtain pseudo labels. The model is further trained using the unlabeled images and pseudo labels to obtain a whole vessel segmentation model.

[0034] In the embodiment of the present invention, the whole blood vessel segmentation model is a semi-supervised learning model.

[0035] In some embodiments, a coronary angiography image is input into a whole-vessel segmentation model to obtain a first segmented image, including: inputting the coronary angiography image into the whole-vessel segmentation model to obtain an initial whole-vessel image; binarizing the initial whole-vessel image according to a first confidence threshold to obtain a first segmented image, and binarizing the initial whole-vessel image according to a second confidence threshold to obtain a second segmented image; wherein the first confidence threshold is less than the second confidence threshold; and determining the first segmented image based on the first segmented image and the second segmented image.

[0036] In the embodiment of the present invention, the above process is a double threshold post-processing process. The output of the above segmentation model is an image with annotated confidence. Each pixel in the image is set with a confidence, and is usually binarized with a threshold of 0.5, that is, pixels greater than 0.5 are processed as blood vessels, and blood vessels less than 0.5 are processed as background. However, the image details in the image obtained by this method are poor, and there is noise, so the recognition effect is poor.

[0037] Therefore, the traditional binarization process can be improved. The confidence threshold can be lowered, for example, from 0.5 to 0.1. It can be found that the details of the image after binarization are greatly improved, but this method will cause the noise to increase further.

[0038] In an embodiment of the present invention, by first segmenting the angiography image according to a traditional method, and then using two different confidence thresholds to obtain a first segmented image with better segmentation details but a large amount of noise, and a second segmented image with slightly worse vascular segmentation details but less noise, it is possible to combine the advantages of the first segmented image and the second segmented image to obtain a final segmented image with good segmentation details and less noise, thereby effectively improving the accuracy of angiography image segmentation.

[0039] In addition, due to factors such as blood vessel blockage, noise interference, and unclear shooting, there will be blood vessel breakpoints in the processed image, resulting in isolated blood vessels outside the main blood vessels in the segmented image. In the binarization process, a higher confidence threshold is likely to cause isolated blood vessels to be misidentified as background noise, resulting in poor blood vessel segmentation effect. Therefore, the main blood vessels and isolated blood vessels are retained by the first segmented image, and the low noise characteristics of the image are retained by the second segmented image, thereby combining to obtain a better segmented image, namely the first segmented image.

[0040] S230, identifying the coronary angiography image to determine the main blood vessel obstruction information.

[0041] In some embodiments, S230 includes: inputting the coronary angiography image into a deep semantic recognition model to determine the various segments of the main blood vessels; and determining the main blood vessel blockage information based on the various segments of the main blood vessels.

[0042] In an embodiment of the present invention, the coronary angiography images of the hospital can be manually annotated by doctors to form a training set and a test set to train the deep semantic recognition model. The segmented blood vessels can specifically include the left main trunk, the anterior descending branch, the circumflex branch, the right coronary artery, etc., which are not limited here. The main blood vessel is usually the clearest blood vessel branch in the image. The deep semantic recognition model first identifies the main blood vessel and then further divides the main blood vessel into segments. The segments that are not divided can be considered to be blocked.

[0043] S240, segmenting the coronary angiography image according to the main vessel occlusion information to obtain a second segmented image.

[0044] In some embodiments, S240 includes: inputting the main vessel obstruction information and the coronary angiography image into the main vessel segmentation model to obtain a second segmented image.

[0045] In the embodiment of the present invention, the main vessel segmentation model is a semi-supervised learning model. A batch of unlabeled angiography images are processed using the trained model, and the prediction results are optimized using a double threshold post-processing method to obtain pseudo labels. The main vessel segmentation model can be obtained by continuing to train the model with unlabeled images and pseudo labels. The image output by the main vessel segmentation model can also be subjected to double threshold post-processing to obtain a second segmented image.

[0046] In some embodiments, the main vessel segmentation model includes an encoder, a first decoder and a second decoder; the main vessel blockage information and the coronary angiography image are input into the main vessel segmentation model to obtain a second segmented image, including: processing the coronary angiography image according to the encoder to obtain initial features; when the main vessel blockage information is non-blocked, inputting the initial features into the first decoder to obtain a second segmented image; when the main vessel blockage information is blocked, inputting the initial features into the second decoder to obtain a second segmented image.

[0047] In the embodiment of the present invention, the training set and the test set of the main vessel segmentation model are divided into two types of images, namely, images with main vessel obstruction and images without main vessel obstruction. The images with main vessel obstruction are used for the training of the second decoder, and the images without main vessel obstruction are used for the training of the first decoder. That is, the first decoder outputs a normal main vessel image, in which the main vessel is relatively long, while the second decoder outputs an obstructed main vessel image, in which the main vessel is relatively short.

[0048] S250, performing feature fusion on the first segmented image and the second segmented image to obtain a coronary angiography image segmentation result.

[0049] In some embodiments, S250 includes: inputting the first segmented image and the second segmented image into a convolutional fusion model to obtain a coronary angiography image segmentation result.

[0050] In an embodiment of the present invention, the convolution fusion model is a neural network model. The convolution fusion model covers the main blood vessels in the second segmented image into the first segmented image, so as to obtain the segmentation result of the coronary angiography image.

[0051] Due to X-ray resolution, 2D grayscale artifacts, dynamic changes in contrast agent filling, etc., there is usually a lot of noise in the contrast image. In order to reduce the impact of noise on segmentation, in some embodiments, the contrast image can also be pre-processed and segmented and down-sampled to form a large-scale image with a scale smaller than the contrast image, a medium-scale image with a scale smaller than the large-scale image, and a small-scale image with a scale smaller than the medium-scale image. Correspondingly, after the large-scale image, the medium-scale image, and the small-scale image are subjected to the blood vessel segmentation in the above embodiment, they are fused together with the segmentation results of the original contrast image and the segmentation results of the main blood vessels into a segmented image as the final recognition result. By segmenting into images of different scales, processing them separately and then merging them, it is possible to take into account both the local and global characteristics of the image, and effectively improve the recognition efficiency.

[0052] In summary, the beneficial effects of the present invention are specifically as follows:

[0053] The main blood vessel is usually the most obvious blood vessel in the image. By segmenting the main blood vessel separately, different main blood vessel images are segmented according to whether it is blocked or not, namely the second segmented image, to avoid combining other blood vessels with the conventional whole blood vessel segmentation when the main blood vessel is blocked, thereby avoiding the segmentation model identifying other clear and long blood vessels as main blood vessels when the main blood vessel is blocked, resulting in blood vessel segmentation errors.

[0054] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0055] Figure 3 FIG. 1 is a schematic diagram of the structure of a coronary angiography image segmentation device considering main vessel obstruction provided by an embodiment of the present invention. Figure 3 As shown, in some embodiments, a coronary angiography image segmentation device 3 considering main vessel obstruction includes:

[0056] An image acquisition module 310 is used to acquire a coronary angiography image;

[0057] The whole blood vessel segmentation module 320 is used to perform whole blood vessel segmentation on the coronary angiography image to obtain a first segmented image;

[0058] The blockage identification module 330 is used to identify the coronary angiography image and determine the blockage information of the main blood vessel;

[0059] The main vessel segmentation module 340 is used to segment the coronary angiography image according to the main vessel occlusion information to obtain a second segmented image;

[0060] The feature fusion module 350 is used to perform feature fusion on the first segmented image and the second segmented image to obtain a coronary angiography image segmentation result.

[0061] Optionally, the blockage identification module 330 is used to input the coronary angiography image into the deep semantic recognition model to determine the various segments of the main blood vessels; and determine the main blood vessel blockage information based on the various segments of the main blood vessels.

[0062] Optionally, the main vessel segmentation module 340 is used to input the main vessel obstruction information and the coronary angiography image into the main vessel segmentation model to obtain a second segmented image.

[0063] Optionally, the main vessel segmentation model includes an encoder, a first decoder and a second decoder; the main vessel segmentation module 340 is used to process the coronary angiography image according to the encoder to obtain initial features; when the main vessel blockage information is non-blocked, the initial features are input into the first decoder to obtain a second segmented image; when the main vessel blockage information is blocked, the initial features are input into the second decoder to obtain a second segmented image.

[0064] Optionally, the whole blood vessel segmentation module 320 is used to input the coronary angiography image into the whole blood vessel segmentation model to obtain a first segmented image.

[0065] Optionally, the whole blood vessel segmentation module 320 is used to input the coronary angiography image into the whole blood vessel segmentation model to obtain an initial whole blood vessel image; binarize the initial whole blood vessel image according to a first confidence threshold to obtain a first segmented image, and binarize the initial whole blood vessel image according to a second confidence threshold to obtain a second segmented image; wherein the first confidence threshold is less than the second confidence threshold;

[0066] A first segmented image is determined according to the first segmented image and the second segmented image.

[0067] Optionally, the feature fusion module 350 is used to input the first segmented image and the second segmented image into a convolutional fusion model to obtain a coronary angiography image segmentation result.

[0068] The coronary angiography image segmentation device considering main vessel obstruction provided in this embodiment can be used to execute the above method embodiments. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0069] Figure 4 Schematic diagram of the structure of the terminal provided by the embodiment of the present invention. Figure 4 As shown, a terminal 4 provided by an embodiment of the present invention includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned coronary angiography image segmentation method considering main vessel obstruction are implemented, for example Figure 2 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned system embodiments are realized, for example Figure 3 The functions of each module are shown.

[0070] Exemplarily, the computer program 42 may be divided into one or more modules / units, one or more modules / units are stored in the memory 41, and are executed by the processor 40 to implement the present invention. One or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the terminal 4.

[0071] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0072] The memory 41 may be an internal storage unit of the terminal 4, such as a hard disk or memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the terminal 4. The memory 41 is used to store computer programs and other programs and data required by the terminal. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0073] An embodiment of the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned embodiment of the method for segmenting coronary angiography images taking into account main vessel obstruction are implemented.

[0074] The computer readable storage medium stores a computer program 42, which includes program instructions. When the program instructions are executed by the processor 40, all or part of the processes in the above-mentioned embodiment method are implemented. The computer program 42 can also be used to instruct related hardware to complete. The computer program 42 can be stored in a computer readable storage medium. When the computer program 42 is executed by the processor 40, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program 42 includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium.

[0075] The computer-readable storage medium may be an internal storage unit of the terminal of any of the foregoing embodiments, such as a hard disk or memory of the terminal. The computer-readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0076] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0077] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0078] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0079] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0080] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0081] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0083] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media can include: any entity or device that can carry computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0084] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A coronary angiography image segmentation method considering main vessel occlusion, characterized in that: include: Obtain coronary angiographic images; Performing whole-vessel segmentation on the coronary angiography image to obtain a first segmented image; Identifying the coronary angiography image to determine main blood vessel obstruction information; Segmenting the coronary angiography image according to the main vessel occlusion information to obtain a second segmented image; Performing feature fusion on the first segmented image and the second segmented image to obtain a coronary angiography image segmentation result; Identifying the coronary angiography image to determine the main blood vessel obstruction information includes: Inputting the coronary angiography image into a deep semantic recognition model to determine the segments of the main blood vessels; Determining the main blood vessel obstruction information according to each segment of the main blood vessel; Segmenting the coronary angiography image according to the main vessel occlusion information to obtain a second segmented image, including: Inputting the main vessel obstruction information and the coronary angiography image into a main vessel segmentation model to obtain a second segmented image; Performing feature fusion on the first segmented image and the second segmented image to obtain a coronary angiography image segmentation result includes: Inputting the first segmented image and the second segmented image into a convolutional fusion model to obtain a coronary angiography image segmentation result; The main vessel segmentation model includes an encoder, a first decoder, and a second decoder; the main vessel occlusion information and the coronary angiography image are input into the main vessel segmentation model to obtain a second segmented image including: Processing the coronary angiography image according to the encoder to obtain initial features; When the main blood vessel obstruction information is non-obstructed, inputting the initial feature into the first decoder to obtain a second segmented image; When the main blood vessel occlusion information is occlusion, the initial feature is input into the second decoder to obtain a second segmented image.

2. The method for segmenting coronary angiography images considering main vessel occlusion according to claim 1, characterized in that: Performing whole-vessel segmentation on the coronary angiography image to obtain a first segmented image includes: The coronary angiography image is input into a whole blood vessel segmentation model to obtain a first segmented image.

3. The method for segmenting coronary angiography images considering main vessel occlusion according to claim 2, characterized in that: The coronary angiography image is input into a whole blood vessel segmentation model to obtain a first segmented image, including: Inputting the coronary angiography image into a whole blood vessel segmentation model to obtain an initial whole blood vessel image; Binarizing the initial whole blood vessel image according to a first confidence threshold to obtain a first segmented image, and binarizing the initial whole blood vessel image according to a second confidence threshold to obtain a second segmented image; wherein the first confidence threshold is less than the second confidence threshold; The first segmented image is determined according to the first segmented image and the second segmented image.

4. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the coronary angiography image segmentation method considering main vessel obstruction as described in any one of claims 1 to 3 are implemented.

5. A contrast image processing system, characterized in that: The device comprises an angiography device and the electronic device as claimed in claim 4 above.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the coronary angiography image segmentation method considering main vessel obstruction as described in any one of claims 1 to 3 above are implemented.

Images