Method, device and storage medium for training a segmentation model for segmenting aneurysms

Abstract

The present application discloses a method, device, and storage medium for training a segmentation model for segmenting aneurysms. The method comprises: acquiring multimodal image data, wherein the multimodal image data includes digital subtraction angiography data, CT angiography data, and magnetic resonance angiography data; performing vessel segmentation and labeling target aneurysms based on the multimodal image data to obtain vessel segmentation results and target aneurysm labeling results; constructing a distance map and labeling data based on the vessel segmentation results and the target aneurysm labeling results; and inputting the vessel segmentation results, the distance map, and the labeling data into a segmentation model to perform aneurysm segmentation to obtain the target aneurysm, thereby training the segmentation model for segmenting aneurysms. Utilizing the solution of the present application, the segmentation accuracy of the segmentation model can be improved to obtain a more accurate target aneurysm.

Description

Technical Field

[0001] The present application generally relates to the technical field of aneurysm segmentation. More specifically, the present application relates to a method for training a segmentation model for segmenting an aneurysm, a method, a device, and a computer-readable storage medium for segmenting an aneurysm. Background Art

[0002] Aneurysm is a type of lesion in the blood vessels, which refers to the thickening of the artery diameter and the manifestation of tumor-like expansion. In physical examination screening, imaging examination of the blood vessels is often used to screen for aneurysms. The aforementioned images include digital subtraction angiography ("DSA"), CT angiography ("CTA") or magnetic resonance angiography ("MRA"). At present, for the segmentation of aneurysms, aneurysms are directly labeled in the image data, and the labeled images are input into the segmentation model for aneurysm segmentation. However, the size of aneurysms in different imaging examinations varies, and direct labeling based on image data cannot balance the characteristics of aneurysms of different sizes. In addition, due to the presence of multiple aneurysms close to each other, especially for small aneurysms close to large arteries, existing segmentation often only segments large aneurysms and ignores small arteries, thereby affecting the accuracy of aneurysm segmentation.

[0003] In view of this, there is an urgent need to provide a solution for training a segmentation model for segmenting aneurysms, so as to improve the segmentation accuracy of the segmentation model and obtain more accurate aneurysm segmentation results. Summary of the Invention

[0004] In order to at least solve one or more of the technical problems mentioned above, the present application proposes, in multiple aspects, a solution for training a segmentation model for segmenting aneurysms.

[0005] In a first aspect, the present application provides a method for training a segmentation model for segmenting aneurysms, comprising: acquiring multimodal image data, wherein the multimodal image data includes digital subtraction angiography data, CT angiography data, and magnetic resonance angiography data; performing blood vessel segmentation and labeling a target aneurysm based on the multimodal image data to obtain a blood vessel segmentation result and a target aneurysm labeling result; constructing a distance map and label data based on the blood vessel segmentation result and the target aneurysm labeling result; and inputting the blood vessel segmentation result, the distance map, and the label data into a segmentation model to perform aneurysm segmentation to obtain a target aneurysm, so as to train the segmentation model for segmenting aneurysms.

[0006] In some embodiments, the distance map is constructed by the following operations: arbitrarily selecting a positioning point in the target aneurysm annotation result; and calculating the shortest path from each pixel point in the foreground area of ​​the blood vessel segmentation result to the positioning point to construct the distance map, wherein the shortest path does not pass through the background area of ​​the blood vessel segmentation result.

[0007] In other embodiments, the label data is constructed by the following operations: setting the corresponding pixel points located in the foreground area of ​​the blood vessel segmentation result and not located in the target aneurysm annotation result as the first label data; and setting the corresponding pixel points located in the target aneurysm annotation result where the positioning point is located as the second label data.

[0008] In some other embodiments, the blood vessel segmentation result, the distance map and the label data are input into a segmentation model to perform aneurysm segmentation to obtain a target aneurysm, so as to train the segmentation model for segmenting aneurysms, including: inputting the blood vessel segmentation result, the distance map, the first label data and the second label data into the segmentation model to perform aneurysm segmentation, and outputting different categories to obtain a target aneurysm, so as to train the segmentation model for segmenting aneurysms.

[0009] In some other embodiments, the label data is constructed by the following operations: setting the corresponding pixel points located in the foreground area of ​​the blood vessel segmentation result and not located in the target aneurysm labeling result as the first label data; setting the corresponding pixel points located in the target aneurysm labeling result that does not contain the positioning point as the second label data; and setting the corresponding pixel points located in the target aneurysm labeling result where the positioning point is located as the third label data.

[0010] In some other embodiments, inputting the blood vessel segmentation result, the distance map and the label data into a segmentation model to perform aneurysm segmentation to obtain a target aneurysm, so as to train the segmentation model for segmenting aneurysms further includes: inputting the blood vessel segmentation result, the distance map, the first label data, the second label data and the third label data into the segmentation model to perform aneurysm segmentation, and outputting different categories to obtain a target aneurysm, so as to train the segmentation model for segmenting aneurysms.

[0011] In some further embodiments, the segmentation model includes a Unet model, an FPN model, or a PSPNet model.

[0012] In a second aspect, the present application provides a method for segmenting an aneurysm, comprising: acquiring image data to be segmented and extracting a binary image and a distance map for vascular segmentation based on the image data to be segmented; and inputting the binary image and the distance map for vascular segmentation into a segmentation model trained by one or more embodiments of the first aspect to perform aneurysm segmentation to obtain a target aneurysm.

[0013] In a third aspect, the present application provides a device comprising: a processor; and a memory on which computer instructions for training a segmentation model for segmenting aneurysms are stored, and when the computer instructions are executed by the processor, multiple embodiments of the aforementioned first aspect are implemented; or computer instructions for segmenting aneurysms are stored, and when the computer instructions are executed by the processor, one embodiment of the aforementioned second aspect is implemented.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium storing computer program instructions for training a segmentation model for segmenting aneurysms, which, when executed by one or more processors, implement multiple embodiments of the aforementioned first aspect; or storing computer instructions for segmenting aneurysms, which, when executed by a processor, implement one embodiment of the aforementioned second aspect.

[0015] Through the scheme for training the segmentation model for segmenting aneurysms as provided above, the embodiment of the present application uses multimodal imaging data, and performs vascular segmentation and aneurysm labeling on the multimodal imaging data to obtain vascular segmentation results and aneurysm labeling results, and at the same time combines the vascular segmentation results and aneurysm labeling results of different imaging data to construct label data. Among them, the vascular segmentation results are consistent in different modalities, so the embodiment of the present application can more accurately label aneurysms through the morphological characteristics of the blood vessels, thereby improving the segmentation accuracy of the segmentation model. In addition, the embodiment of the present application adds a distance feature (i.e., a distance map), which can better distinguish the target aneurysm from other aneurysms to improve the segmentation accuracy of small aneurysms. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other objects, features and advantages of the exemplary embodiments of the present application will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0017] Figure 1 is an exemplary flowchart illustrating a method for training a segmentation model for segmenting an aneurysm according to an embodiment of the present application;

[0018] Figure 2is an exemplary flowchart illustrating an overall process of training a segmentation model for segmenting an aneurysm according to an embodiment of the present application;

[0019] Figure 3 is another exemplary flowchart illustrating the overall process of training a segmentation model for segmenting an aneurysm according to an embodiment of the present application;

[0020] Figure 4 is an exemplary flow chart illustrating a method for segmenting an aneurysm according to an embodiment of the present application;

[0021] Figure 5 is a block diagram showing an exemplary structure of a device according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0023] It should be understood that the terms "include" and "comprising" used in the description and claims of this application indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0024] It should also be understood that the terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this specification and claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" as used in this specification and claims refers to any and all possible combinations of one or more of the associated listed items, including and including these combinations.

[0025] As used in this specification and claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0026] The specific implementation of the present application will be described in detail below with reference to the accompanying drawings.

[0027] Figure 1 FIG. 1 is an exemplary flow chart illustrating a method 100 for training a segmentation model for segmenting an aneurysm according to an embodiment of the present application. Figure 1 As shown in , the method 100 includes: step S101: acquiring multimodal image data, wherein the multimodal image data includes digital subtraction angiography data, CT angiography data, and magnetic resonance angiography data; step S102: performing blood vessel segmentation and labeling target aneurysms based on the multimodal image data to obtain blood vessel segmentation results and target aneurysm labeling results; step S103: constructing a distance map and label data based on the blood vessel segmentation results and the target aneurysm labeling results; and step S104: inputting the blood vessel segmentation results, the distance map, and the label data into a segmentation model to perform aneurysm segmentation to obtain the target aneurysm, so as to train the segmentation model for segmenting aneurysms.

[0028] First, in step S101, multimodal imaging data is acquired. This multimodal imaging data may include digital subtraction angiography data, CT angiography data, and magnetic resonance angiography data. Digital subtraction angiography data is the gold standard for screening and diagnosis of various vascular diseases, including aneurysm diagnosis and measurement, while CT angiography data and magnetic resonance angiography data can be used for aneurysm screening and follow-up. By using these three modal data for segmentation model training, the present embodiment can significantly improve the performance of the segmentation model.

[0029] Then, at step S102, blood vessel segmentation is performed based on the multimodal imaging data and the target aneurysm is labeled to obtain a blood vessel segmentation result and a target aneurysm labeling result. In some embodiments, image processing methods or deep learning methods may be used to perform blood vessel segmentation, wherein the aforementioned image processing methods may include but are not limited to image edge detection and image morphology methods. The aforementioned deep learning method may be based on an existing trained segmentation model to perform blood vessel segmentation to obtain a blood vessel segmentation result. This application does not impose any restrictions on this, and the aforementioned blood vessel segmentation result is a binary image. In some implementation scenarios, the aforementioned aneurysm labeling may be performed manually or automatically to label the target aneurysm area in the blood vessel segmentation result to obtain a target aneurysm labeling result.

[0030] Based on the vessel segmentation results and target aneurysm labeling results obtained above, in step S103, a distance map and label data are constructed based on the vessel segmentation results and the target aneurysm labeling results. The consistency of the vessel segmentation results across different modalities facilitates aneurysm morphological analysis, leading to more accurate aneurysm labeling. Thus, combining the vessel segmentation results and the target aneurysm labeling results to construct label data can improve the accuracy of target aneurysm labeling, thereby enhancing the precision of subsequent segmentation model training.

[0031] In some embodiments, the distance map can be constructed by the following operations: arbitrarily selecting a positioning point in the target aneurysm annotation result, calculating the shortest path from each pixel in the foreground area of ​​the vessel segmentation result to the positioning point, and constructing a distance map, wherein the shortest path does not pass through the background area of ​​the vessel segmentation result. Specifically, a positioning point is randomly selected on the target aneurysm annotation result, and for each point in the foreground area of ​​the vessel segmentation result, the shortest path d to the positioning point is calculated. This shortest path d does not pass through the background area of ​​the vessel segmentation result, that is, for each point in the background area, the corresponding path d = 0. Based on this, a distance map can be extracted to more accurately distinguish different aneurysms and ensure that small aneurysms are segmented, thereby improving segmentation accuracy.

[0032] In some embodiments, label data can be constructed by the following operations: corresponding pixels within the foreground region of the vessel segmentation result but not within the target aneurysm annotation result are set as first label data, and corresponding pixels within the target aneurysm annotation result where the anchor point is located are set as second label data. That is, the vessel pixel annotation is set as the first label data, for example, the label can be set to 1. Pixels within the target aneurysm annotation result, where the anchor point is also within the target aneurysm annotation result, are set as second label data, for example, the label can be set to 2. Label 1 corresponds to a non-aneurysm, and label 2 corresponds to a target aneurysm.

[0033] Furthermore, at step S104, the vessel segmentation results, distance map, and label data are input into a segmentation model to perform aneurysm segmentation to obtain target aneurysms, thereby training the segmentation model for aneurysm segmentation. In some embodiments, the vessel segmentation results, the distance map, the first label data, and the second label data can be input into a segmentation model to perform aneurysm segmentation, and different categories can be output to obtain target aneurysms, thereby training the segmentation model for aneurysm segmentation. That is, the vessel segmentation results and the distance map are used as input data, and the first and second label data are used as labels to train the segmentation model for aneurysm segmentation. In some implementation scenarios, the aforementioned segmentation model can be, for example, a Unet model, an FPN model, or a PSPNet model.

[0034] In combination with the above description, it can be seen that the embodiment of the present application performs blood vessel segmentation and labels aneurysms on digital subtraction angiography data, CT angiography data and magnetic resonance angiography data to obtain blood vessel segmentation results and aneurysm labeling results, and at the same time trains the segmentation model by combining the label data constructed by the blood vessel segmentation results and aneurysm labeling results. Based on this, the problem that the image features cannot be aligned (that is, lack of consistency) when directly segmenting aneurysms from the image can be avoided, thereby improving the accuracy of aneurysm identification. In addition, the embodiment of the present application also adds a distance feature, which can better distinguish the target aneurysm from other aneurysms to improve the segmentation accuracy of small aneurysms. Furthermore, the embodiment of the present application can more accurately distinguish large aneurysms from small aneurysms by calculating the shortest distance between the positioning point and the blood vessel foreground pixel, thereby improving the identification accuracy of the target aneurysm.

[0035] Figure 2 FIG. 1 is an exemplary flow chart showing the overall process of training a segmentation model for segmenting aneurysms according to an embodiment of the present application. It should be understood that Figure 2 is the above Figure 1 A specific implementation of method 100, so the above Figure 1 The description also applies to Figure 2 .

[0036] like Figure 2 As shown in FIG, in step S201, digital subtraction angiography data, CT angiography data, and magnetic resonance angiography data are acquired. Next, in step S202, vessel segmentation is performed based on the aforementioned three multimodal imaging data to obtain a vessel segmentation result. In some embodiments, vessel segmentation can be performed using, for example, edge detection, morphology, or existing segmentation models to obtain a vessel segmentation result. In step S203, target aneurysms are labeled within the vessel segmentation result to obtain a target aneurysm labeling result.

[0037] Furthermore, at step S204, a positioning point is randomly selected in the target aneurysm annotation result, and at step S205, the shortest path from each pixel in the foreground region of the vessel segmentation result to the positioning point is calculated to obtain a distance map. The shortest path does not pass through the background region of the vessel segmentation result.

[0038] The figure further illustrates that, at step S206, corresponding pixels within the foreground region of the vessel segmentation result but not within the target aneurysm annotation result are set as first label data, and, at step S207, corresponding pixels within the target aneurysm annotation result at the location of the anchor point are set as second label data. Based on the obtained vessel segmentation result, distance map, first and second label data, at step S208, the vessel segmentation result, distance map, first label data, and second label data are input into a segmentation model for training to obtain the target aneurysm, thereby obtaining a trained segmentation model.

[0039] In some embodiments, the embodiments of the present application can also construct label data by the following operations: setting the corresponding pixel points located in the foreground area of ​​the blood vessel segmentation result and not located in the target aneurysm annotation result as the first label data, setting the corresponding pixel points located in the target aneurysm annotation result that does not contain the positioning point as the second label data, and setting the corresponding pixel points located in the target aneurysm annotation result where the positioning point is located as the third label data. That is, the blood vessel pixel annotation is set as the first label data, for example, the label can be set to 1. The pixel points located in the target aneurysm annotation result but not containing the positioning point are set as the second label data, for example, the label can be set to 2. The pixel points located in the target aneurysm annotation result and the positioning point are also in the target aneurysm annotation result are set as the third label data, for example, the label can be set to 3. Among them, label 1 corresponds to non-aneurysm, label 2 corresponds to other aneurysms, and label 3 corresponds to the target aneurysm. Based on this, the target aneurysm and other aneurysms can be subdivided to further improve the segmentation accuracy.

[0040] In some embodiments, the vessel segmentation result, the distance map, the first label data, the second label data, and the third label data can be input into a segmentation model to perform aneurysm segmentation, and different categories can be output to obtain target aneurysms to train the segmentation model for aneurysm segmentation. Specifically, the segmentation model is trained using the further constructed first, second, and third label data as labels, and the vessel segmentation result and the distance map as input data.

[0041] Figure 3 FIG. 1 is another exemplary flow chart illustrating the overall training of a segmentation model for segmenting an aneurysm according to an embodiment of the present application. It should be understood that Figure 3 is the above Figure 1 Another specific implementation of the method 100, so the above Figure 1 The description also applies to Figure 3 .

[0042] like Figure 3As shown in FIG, in step S301, digital subtraction angiography data, CT angiography data, and magnetic resonance angiography data are acquired. Next, in step S302, vessel segmentation is performed based on the aforementioned three multimodal imaging data to obtain a vessel segmentation result. In some embodiments, vessel segmentation can be performed using, for example, edge detection, morphology, or existing segmentation models to obtain a vessel segmentation result. In step S303, target aneurysms are labeled within the vessel segmentation result to obtain a target aneurysm labeling result.

[0043] Furthermore, in step S304, a locating point is arbitrarily selected from the target aneurysm labeling result, and in step S305, the shortest path from each pixel in the foreground region of the vessel segmentation result to the locating point is calculated to obtain a distance map. Next, in steps S306, S307, and S308, first label data, second label data, and third label data are constructed. Specifically, the first label data is assigned to corresponding pixels within the foreground region of the vessel segmentation result that are not within the target aneurysm labeling result, the second label data is assigned to corresponding pixels within the target aneurysm labeling result that does not contain the locating point, and the third label data is assigned to corresponding pixels within the target aneurysm labeling result where the locating point is located.

[0044] After obtaining the aforementioned blood vessel segmentation results, distance map and label data, at step S309, the blood vessel segmentation results, distance map, first label data, second label data and third label data are input into the segmentation model for training to obtain the target aneurysm, so as to obtain a trained segmentation model.

[0045] Figure 4 FIG. 4 is an exemplary flow chart showing a method 400 for segmenting an aneurysm according to an embodiment of the present application. Figure 4 As shown in , the method 400 includes: step S401: acquiring image data to be segmented and extracting a binary image and a distance image of blood vessel segmentation based on the image data to be segmented; step S402: inputting the binary image and the distance image of blood vessel segmentation into the trained segmentation model to perform aneurysm segmentation to obtain a target aneurysm.

[0046] In step S401, image data to be segmented is acquired, and a binary image and a distance map for vessel segmentation are extracted based on the image data to be segmented. As previously mentioned, methods such as image edge detection, image morphology, or deep learning can be used to extract the binary image for vessel segmentation. In some embodiments, the distance map can be obtained by calculating the shortest path from a location point in the target aneurysm annotation result to a pixel point in the foreground region of the vessel segmentation result.

[0047] Next, at step S402, the binary image and distance map of the vessel segmentation are input into the trained segmentation model to perform aneurysm segmentation, thereby obtaining aneurysm segmentation results. Specifically, the binary image and distance map of the vessel segmentation are directly input into the trained segmentation model, and the aneurysm segmentation results for different categories are output. For example, the output may include non-aneurysms and target aneurysms corresponding to labels 1 and 2; alternatively, the output may include non-aneurysms, other aneurysms, and target aneurysms corresponding to labels 1, 2, and 3.

[0048] Based on the above, it can be seen that the embodiment of the present application extracts vascular segmentation results and labels aneurysms on multimodal data to simultaneously combine vascular-related features and aneurysm labeling results to construct label data, and adds distance features to train the segmentation model. Based on this, it can overcome the problem of image feature alignment when directly segmenting aneurysms from images, and can more accurately label aneurysms and better distinguish target aneurysms from other aneurysms to improve the segmentation accuracy of small aneurysms. Furthermore, the embodiment of the present application also uses more detailed labeling to more accurately distinguish target aneurysms from other aneurysms to further improve segmentation accuracy.

[0049] Figure 5 is an exemplary structural block diagram of a device 500 according to an embodiment of the present application. It is understood that the device 500 may include the apparatus of the embodiment of the present application, and the device implementing the solution of the present application may be a single device (such as a computing device) or a multi-function device including various peripheral devices.

[0050] like Figure 5 As shown in , the device of the present application may also include a central processing unit or central processing unit ("CPU") 511, which may be a general-purpose CPU, a dedicated CPU, or other information processing and program execution unit. Further, the device 500 may also include a large-capacity memory 512 and a read-only memory ("ROM") 513, wherein the large-capacity memory 512 may be configured to store various types of data, including various multimodal data, blood vessel segmentation results, distance maps and aneurysm annotation results, algorithm data, intermediate results, and various programs required to run the device 500. The ROM 513 may be configured to store data and instructions required for power-on self-test of the device 500, initialization of various functional modules in the system, basic input / output drivers of the system, and booting the operating system.

[0051] Optionally, the device 500 may further include other hardware platforms or components, such as the tensor processing unit ("TPU") 514, graphics processing unit ("GPU") 515, field programmable gate array ("FPGA") 516, and machine learning unit ("MLU") 517 shown. It will be understood that although multiple hardware platforms or components are shown in the device 500, these are merely exemplary and non-limiting, and those skilled in the art may add or remove corresponding hardware according to actual needs. For example, the device 500 may only include a CPU, related storage devices, and interface devices to implement the method for training a segmentation model for segmenting an aneurysm or the method for segmenting an aneurysm of the present application.

[0052] In some embodiments, to facilitate the transmission and interaction of data with an external network, the device 500 of the present application further includes a communication interface 518, which can be connected to a local area network / wireless local area network ("LAN / WLAN") 505 via the communication interface 518, and then connected to a local server 506 or the Internet ("Internet") 507 via the LAN / WLAN. Alternatively or additionally, the device 500 of the present application can also be directly connected to the Internet or a cellular network via the communication interface 518 based on wireless communication technology, such as wireless communication technology based on the third generation ("3G"), fourth generation ("4G"), or fifth generation ("5G") generations. In some application scenarios, the device 500 of the present application can also access a server 508 and a database 509 of an external network as needed to obtain various known algorithms, data, and modules, and can remotely store various data, such as various data or instructions for presenting, for example, multimodal data, vessel segmentation results, distance maps, and aneurysm annotation results.

[0053] The peripheral devices of the device 500 may include a display device 502, an input device 503 and a data transmission interface 504. In one embodiment, the display device 502 may include, for example, one or more speakers and / or one or more visual displays, which are configured to train the segmentation model for segmenting aneurysms of the present application or to provide voice prompts and / or image video displays for segmenting aneurysms. The input device 503 may include other input buttons or controls such as a keyboard, a mouse, a microphone, a gesture capture camera, etc., which are configured to receive input of audio data and / or user instructions. The data transmission interface 504 may include, for example, a serial interface, a parallel interface or a universal serial bus interface ("USB"), a small computer system interface ("SCSI"), a serial ATA, a FireWire ("FireWire"), a PCI Express and a high-definition multimedia interface ("HDMI"), etc., which are configured for data transmission and interaction with other devices or systems. According to the solution of the present application, the data transmission interface 504 can receive multimodal data collected from CT and MRI equipment and transmit data or results including multimodal data or various other types to the device 500.

[0054] The CPU 511, mass storage 512, ROM 513, TPU 514, GPU 515, FPGA 516, MLU 517, and communication interface 518 of the device 500 of the present application can be interconnected via a bus 519 and can interact with peripheral devices via the bus. In one embodiment, the CPU 511 can control other hardware components in the device 500 and its peripheral devices via the bus 519.

[0055] Combination of the above Figure 5 The devices that can be used to implement the present application are described. It should be understood that the device structures or architectures herein are merely exemplary, and the implementation methods and implementation entities of the present application are not limited thereto, but can be modified without departing from the spirit of the present application.

[0056] According to the above description in combination with the accompanying drawings, those skilled in the art can also understand that the embodiments of the present application can also be implemented by software programs. Therefore, the present application also provides a computer-readable storage medium, which stores computer-readable instructions for training a segmentation model for segmenting an aneurysm or for segmenting an aneurysm. When the computer-readable instructions are executed by one or more processors, they can be used to implement the present application in combination with the accompanying drawings. Figure 1 The method for training a segmentation model for segmenting aneurysms described in the present application; or implementing the method in combination with the attached Figure 4 A method for segmenting an aneurysm is described.

[0057] It should be noted that although the operations of the present method are described in a particular order in the accompanying drawings, this does not require or imply that the operations must be performed in that particular order, or that all of the operations shown must be performed to achieve the desired results. Rather, the steps depicted in the flowcharts may be performed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into a single step, and / or a single step may be broken down into multiple steps.

[0058] It should be understood that when the terms "first," "second," "third," and "fourth," etc., are used in the claims, specification, and drawings of this application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "comprise" and "comprising" used in the specification and claims of this application indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof.

[0059] It should also be understood that the terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this specification and claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" as used in this specification and claims refers to any and all possible combinations of one or more of the associated listed items, including and including these combinations.

[0060] Although the implementation methods of this application are as described above, the contents are only examples adopted to facilitate understanding of this application and are not intended to limit the scope and application scenarios of this application. Any technician in the technical field described in this application can make any modifications and changes in the form and details of implementation without departing from the spirit and scope disclosed in this application, but the scope of patent protection of this application shall still be based on the scope defined by the attached claims.

[0061] In addition, the collection and acquisition of various data in this application complies with relevant laws and regulations and is authorized by the data provider. Any organization or individual that needs to obtain external data must obtain authorization in accordance with the law and ensure data security. They must not illegally collect, use, process, or transmit unauthorized or unprotected data, nor illegally buy, sell, provide, or disclose unauthorized or unprotected data.

Claims

1. A method for training a segmentation model for segmenting an aneurysm, comprising: Acquiring multimodal imaging data, wherein the multimodal imaging data includes digital subtraction angiography data, CT angiography data, and magnetic resonance angiography data; Performing blood vessel segmentation and marking target aneurysms based on the multimodal image data to obtain blood vessel segmentation results and target aneurysm marking results; constructing a distance map and label data according to the blood vessel segmentation result and the target aneurysm annotation result; as well as Inputting the blood vessel segmentation result, the distance map and the label data into a segmentation model to perform aneurysm segmentation to obtain a target aneurysm, so as to train the segmentation model for segmenting aneurysms. The distance map is constructed by the following operations: arbitrarily selecting a positioning point in the target aneurysm marking result; and Calculating the shortest path from each pixel point in the foreground area of ​​the blood vessel segmentation result to the positioning point to construct the distance map, wherein the shortest path does not pass through the background area of ​​the blood vessel segmentation result; The label data is constructed by the following operations: setting corresponding pixel points located in the foreground area of ​​the blood vessel segmentation result and not located in the target aneurysm annotation result as first label data; and The corresponding pixel point located in the target aneurysm annotation result where the positioning point is located is set as the second label data.

2. The method according to claim 1, wherein inputting the blood vessel segmentation result, the distance map, and the label data into a segmentation model to perform aneurysm segmentation to obtain a target aneurysm, so as to train the segmentation model for segmenting aneurysms, comprises: The blood vessel segmentation result, the distance map, the first label data and the second label data are input into the segmentation model to perform aneurysm segmentation, and different categories are output to obtain target aneurysms to train the segmentation model for segmenting aneurysms.

3. The method according to claim 1, wherein the tag data is constructed by: Setting corresponding pixel points located in the foreground area of ​​the blood vessel segmentation result and not located in the target aneurysm annotation result as first label data; setting corresponding pixel points located in the target aneurysm annotation result excluding the positioning point as second label data; and The corresponding pixel point located in the target aneurysm marking result where the positioning point is located is set as the third label data.

4. The method according to claim 3, wherein inputting the blood vessel segmentation result, the distance map, and the label data into a segmentation model to perform aneurysm segmentation to obtain a target aneurysm, so as to train the segmentation model for segmenting aneurysms, further comprises: The blood vessel segmentation result, the distance map, the first label data, the second label data and the third label data are input into the segmentation model for aneurysm segmentation, and different categories are output to obtain target aneurysms to train the segmentation model for aneurysm segmentation.

5. The method according to claim 1, wherein the segmentation model comprises a Unet model, an FPN model or a PSPNet model.

6. A method for segmenting an aneurysm, comprising: Acquiring image data to be segmented and extracting a binary image and a distance image for blood vessel segmentation based on the image data to be segmented; as well as The binary image of the blood vessel segmentation and the distance image are input into the segmentation model trained according to the method according to any one of claims 1 to 5 to perform aneurysm segmentation to obtain a target aneurysm.

7. A computing device comprising: processor; as well as A memory storing computer instructions for training a segmentation model for segmenting an aneurysm, which, when executed by a processor, implements the method according to any one of claims 1 to 5; or storing computer instructions for segmenting an aneurysm, which, when executed by a processor, implements the method according to claim 6.

8. A computer-readable storage medium having stored thereon computer program instructions for training a segmentation model for segmenting an aneurysm, wherein when the computer program instructions are executed by one or more processors, the method according to any one of claims 1 to 5 is implemented; or a computer program instruction for segmenting an aneurysm is stored thereon, wherein when the computer program instructions are executed by one or more processors, the method according to claim 6 is implemented.

Images