Method and device for training detection model for detecting vascular adhesion and storage medium

Abstract

The invention discloses a method and equipment for training a detection model for detecting vascular adhesion and a storage medium. The method comprises the following steps: acquiring multi-modal image data, wherein the multi-modal image data comprises digital subtraction angiography data, CT angiography data and magnetic resonance angiography data; performing blood vessel segmentation based on the multi-modal image data to obtain a blood vessel map and blood vessel information; extracting a binary image of a single blood vessel according to the blood vessel image and the blood vessel information, and marking whether the single blood vessel passes through an adhered blood vessel; constructing training data based on the multi-modal image data, the binary image of the single blood vessel and a labeling result; and inputting the training data into a detection model for vascular adhesion detection to obtain a detection result, so as to train the detection model for vascular adhesion detection. By means of the scheme, accurate positioning and efficient detection of vascular adhesion can be improved.

Description

Technical Field

[0001] The present application generally relates to the technical field of vascular adhesion detection, and more specifically, to a method for training a detection model for detecting vascular adhesion, a method for detecting vascular adhesion, a device, and a computer-readable storage medium. Background Art

[0002] Digital subtraction angiography (DSA), the gold standard for diagnosing vascular diseases, reveals a tree-like structure in intracranial vessels. Existing technologies use vessel segmentation and skeletonization algorithms to extract centerlines and construct vascular maps. However, due to volume effects, vascular adhesions tend to form ring-like structures, resulting in reduced efficiency, poor stability, and even program crashes in path tracing algorithms. Traditional methods rely on manual annotation or simple geometric analysis, which cannot efficiently and accurately detect vascular adhesions.

[0003] In view of this, there is an urgent need to provide a solution for training a detection model for detecting vascular adhesions in order to improve the accurate positioning and efficient detection of vascular adhesions. Summary of the Invention

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

[0005] In a first aspect, the present application provides a method for training a detection model for detecting vascular adhesions, comprising: acquiring multimodal image data, wherein the multimodal image data includes digital subtraction angiography data, CT angiography data, and magnetic resonance angiography data; performing vascular segmentation based on the multimodal image data to obtain a vascular map and vascular information; extracting a binary image of a single blood vessel based on the vascular map and the vascular information, and annotating whether the image passes through an adhesion vessel; constructing training data based on the multimodal image data, the binary image of the single blood vessel, and the annotated results; and inputting the training data into a detection model to perform vascular adhesion detection to obtain a detection result, thereby training the detection model for vascular adhesion detection.

[0006] In some embodiments, the blood vessel information includes at least position information and radius information of each pixel point on the blood vessel map.

[0007] In other embodiments, the binary image of the single blood vessel is extracted by the following operations: determining a target pixel point on the single blood vessel and a radius at the target pixel point based on the blood vessel map and the blood vessel information; setting the pixels within an area with the radius at the target pixel point as the center to the target value, and setting the remaining pixels to 0, to extract the binary image of the single blood vessel.

[0008] In some further embodiments, it further includes: judging whether a pixel point passes through an adhesion vessel according to the vessel map and the vessel information; and marking the pixel point as having passed through an adhesion vessel and not having passed through an adhesion vessel based on the judgment result to obtain the marking result.

[0009] In some further embodiments, the method further includes: performing maximum bounding box cropping on the single blood vessel to obtain the cropped single blood vessel; and constructing the training data based on the multimodal imaging data, the binary image of the cropped single blood vessel, and the annotation results.

[0010] In some further embodiments, the detection model includes an encoder and a classifier, and the training data is input into the detection model to perform vascular adhesion detection to obtain a detection result, so as to train the detection model for vascular adhesion detection: based on the training data, the encoder is used to perform an encoding operation to obtain an encoding result; and the classifier is used to perform a classification operation on the encoding result to obtain a detection result of vascular adhesion detection, so as to train the detection model for vascular adhesion detection.

[0011] In some further embodiments, the detection model comprises a machine learning model or a deep learning model.

[0012] In a second aspect, the present application provides a method for detecting vascular adhesions, comprising: acquiring multimodal image data, wherein the multimodal image data includes digital subtraction angiography data, CT angiography data, and magnetic resonance angiography data; performing vascular segmentation based on the multimodal image data to acquire a vascular map and vascular information; extracting a binary image of a single blood vessel based on the vascular map and the vascular information; and inputting the multimodal image data and the binary image of the single blood vessel into a detection model trained according to one or more embodiments of the first aspect to perform vascular adhesion detection to obtain a detection result.

[0013] In a third aspect, the present application provides a device comprising: a processor; and a memory storing computer instructions for training a detection model for detecting vascular adhesion, which, when executed by the processor, implement multiple embodiments of the aforementioned first aspect; or storing computer instructions for detecting vascular adhesion, which, when executed by the processor, implement one embodiment of the aforementioned second aspect.

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

[0015] Through the scheme for training a detection model for detecting vascular adhesions as provided above, the embodiment of the present application uses multimodal data to provide the model with multi-dimensional feature input by fusing different imaging methods, thereby enhancing its adaptability to complex vascular scenes; extracting a binary image of a single blood vessel through the vascular map and vascular information, compensating for the blurred vascular boundaries caused by grayscale overlap or noise interference in the original image, and providing clear geometric clues for the model; inputting the original multimodal data and the binary image into the detection model for training simultaneously, so that the model processes the grayscale information of the original image and the spatial structure information of the binary image simultaneously, which can enhance the spatial positioning accuracy of the adhesion position. The combined effect of the two enables the model to have stronger cross-modal generalization performance, avoiding overfitting caused by single modality training. 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 detection model for detecting vascular adhesion according to an embodiment of the present application;

[0018] Figure 2 is an exemplary flowchart illustrating an overall process of training a detection model for detecting vascular adhesion according to an embodiment of the present application;

[0019] Figure 3 is an exemplary schematic diagram showing a partial blood vessel segment according to an embodiment of the present application;

[0020] Figure 4 is an exemplary flowchart illustrating a method for detecting vascular adhesion 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 them. 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 detection model for detecting vascular adhesion 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 based on the multimodal image data to obtain a blood vessel map and blood vessel information; step S103: extracting a binary image of a single blood vessel based on the blood vessel map and blood vessel information, and marking whether it passes through an adhesion vessel; step S104: constructing training data based on the multimodal image data, the binary image of the single blood vessel, and the marking results; and step S105: inputting the training data into a detection model to perform vascular adhesion detection to obtain a detection result, thereby training the detection model for vascular adhesion detection.

[0028] First, in step S101, multimodal imaging data is collected. The multimodal imaging data may include digital subtraction angiography data, CT angiography data, and magnetic resonance angiography data. Among them, digital subtraction angiography data is the gold standard for screening and diagnosis of various vascular diseases, which can provide details of the vascular lumen; while CT angiography data and magnetic resonance angiography data can also be used for vascular disease screening, follow-up, etc., respectively supplementing the spatial relationship between blood vessels and surrounding tissues and displaying hemodynamic characteristics. By using three modal data for the training of the detection model, the embodiment of the present application can cover the vascular structure information of different imaging principles and improve the adaptability of the model to complex scenes.

[0029] Next, in step S102, vessel segmentation is performed based on the multimodal imaging data to obtain a vessel map and vessel information. In some embodiments, vessel segmentation can be performed using image processing methods or deep learning methods. Such image processing methods may include, but are not limited to, image edge detection and image morphology. Deep learning methods may be based on existing trained segmentation models for vessel segmentation, and this application imposes no restrictions on this. Vessel information can be obtained from the segmented vessels using, for example, the sknw library. In some embodiments, vessel information may include, but is not limited to, the position and radius information of each pixel on the vessel map.

[0030] Based on the vascular map and vascular information obtained above, in step S103, a binary image of a single vessel is extracted based on the vascular map and vascular information, and whether it passes through adhesion vessels is noted. In some embodiments, the binary image of a single vessel can be extracted by the following operation: a target pixel and a radius at the target pixel are determined on the single vessel based on the vascular map and the vascular information. Pixels within the radius of the target pixel, centered on the target pixel, are set to a target value (e.g., 1), and all other pixels are set to 0 to extract the binary image of the single vessel. This ensures the smoothness and integrity of the vascular boundary and effectively suppresses noise interference. The overlay operation strengthens the continuity of the main vascular trunk, eliminates isolated noise points, and provides clear structural feature input for the model.

[0031] As an example, assume that the target pixel point on a single blood vessel is Xi (i=1~n). With Xi as the center, the pixels within a radius ri of the target pixel point Xi are set to 1, and the remaining pixels are set to 0 to extract the binary image X_binary of the single blood vessel.

[0032] In some embodiments, a vascular map and vascular information can be used to determine whether a target node passes through an adhesion vessel. Based on the determination, the target node is labeled as either having passed through an adhesion vessel or not, yielding a labeling result. This creates two types of labels: one for passing through an adhesion vessel, whose value can be set to 1; the other for not passing through an adhesion vessel, whose value can be set to 0. In some implementations, a threshold can be set based on, for example, vessel radius or grayscale differences in the vascular map. When the difference in radius between adjacent vessel segments exceeds the threshold, adhesion is determined.

[0033] Furthermore, in step S104, training data is constructed based on the multimodal imaging data, the binary image of a single vessel, and the annotation results. For example, assume that the multimodal imaging data is denoted as X, the binary image of a single vessel is denoted as X_binary, and the annotation result indicates that the image passes through an adhesion vessel, with a value of 1. In this scenario, the training data [[X, X_binary], 1] can be obtained. Similarly, if the annotation result indicates that the image does not pass through an adhesion vessel, with a value of 0, the training data [[X, X_binary], 0] can be obtained.

[0034] In some implementation scenarios, a single vessel can be cropped using a maximum bounding box to obtain the cropped vessel. Training data can then be constructed based on the multimodal imaging data, the cropped binary image of the single vessel, and the annotation results. Based on this, a single vessel is cropped using a maximum bounding box, focusing on areas with high adhesion risk (such as branch intersections) to reduce interference from redundant background information. The cropped image blocks are standardized in size to reduce computational complexity while retaining the complete vessel structure, ensuring that the model can quickly locate adhesions during the inference phase and improving detection speed.

[0035] As you can understand, the maximum bounding box is the smallest rectangular area that contains the target object (a single blood vessel). The boundary is determined by calculating the coordinate extremes (x_min, x_max, y_min, y_max) of all pixels in the vessel segment in the vessel image, ensuring complete coverage of the vessel segment while minimizing redundant background. As an example, let the cropped binary image of a single blood vessel be denoted as X_binary_box, the multimodal imaging data be denoted as X, and the annotation result is "passing through adhesion vessels" with a value of 1. In this scenario, the training data is [[X,X_binary_box],1]. Alternatively, the annotation result is "passing through adhesion vessels" with a value of 0, resulting in the training data [[X,X_binary_box],0].

[0036] Finally, at step S105, the training data is input into the detection model to perform vascular adhesion detection to obtain a detection result, thereby training the detection model for vascular adhesion detection. In some embodiments, the detection model may include a machine learning model or a deep learning model. In other embodiments, the detection model may include an encoder and a classifier. Specifically, based on the training data, an encoder is used to perform an encoding operation to obtain an encoding result, and then a classifier is used to classify the encoding result to obtain a detection result for vascular adhesion detection, thereby training the detection model for vascular adhesion detection.

[0037] In an exemplary scenario, if the encoder is denoted as encoder and the classifier is denoted as clf, the encoder can first perform an encoding operation to obtain the encoding result feature = encoder(X, X_binary). For a binary image of a cropped single blood vessel, feature = encoder(X, X_binary_box). Next, the classifier performs a classification operation pred = clf(feature) on the encoding result and calculates a cross-entropy loss function, such as Loss = CrossEntroy(label, pred), for backpropagation to update the parameters of the encoder and classifier clf to train the detection model for vascular adhesion detection. Label represents the label value.

[0038] Combined with the above description, it can be seen that the multimodal data of the embodiment of the present application provides multi-dimensional feature input for the model by fusing different imaging methods, enhancing adaptability to complex vascular scenes and reducing the risk of misjudgment caused by imaging artifacts of a single modality; through vessel segmentation and vessel map extraction, a structured input basis is provided for adhesion detection, ensuring accurate representation of vessel morphology and spatial position. By extracting a single vessel binary map and superimposing a spherical region, discrete structural features (such as connected areas and changes in vessel diameter) are generated to compensate for the blurred vessel boundaries caused by grayscale overlap or noise interference in the original image, providing clear geometric clues for the model. Furthermore, a single vessel is cropped by the maximum bounding box to avoid focusing on areas with high adhesion incidence, reduce redundant background information interference, and standardize the input size, thereby improving detection efficiency.

[0039] Furthermore, the present embodiment achieves joint feature extraction through a cascaded architecture of encoders and classifiers. Combining multimodal training data covering different imaging conditions with a unified binary image representation of vascular structure, this model possesses stronger cross-modal generalization performance and avoids overfitting caused by single-modality training. Ultimately, end-to-end training optimizes feature transfer efficiency, enabling accurate identification of vascular adhesion locations. This addresses the problem of misidentification of adhesions caused by volume effects in traditional methods, improving the reliability of vascular segmentation results and the stability of subsequent clinical applications.

[0040] Figure 2 FIG. 1 is an exemplary flow chart showing the overall process of training a detection model for detecting vascular adhesion according to an embodiment of the present application. Figure 2 As shown in , at step S201, multimodal image data is collected, wherein the multimodal image data includes digital subtraction angiography data, CT angiography data, and magnetic resonance angiography data. Then, at step S202, blood vessel segmentation is performed based on the multimodal image data to obtain a blood vessel map and blood vessel information. Specifically, blood vessel segmentation can be performed by image processing methods or deep learning methods, and blood vessel information (such as the position information and radius information of each pixel point) can be obtained using, for example, the sknw library. At step S203, a single blood vessel is cropped with a maximum bounding box to obtain a cropped single blood vessel, and at step S204, training data is constructed based on the multimodal image data, the binary map of the cropped single blood vessel, and the annotation results to obtain training data. Further, the training data is input into the detection model, and at step S205, an encoder is used to perform an encoding operation to obtain an encoding result. At step S206, a classifier is used to perform a classification operation on the encoding result, and at step S207, a loss function (such as cross entropy loss) is calculated to train a detection model for vascular adhesion detection, so as to obtain a trained detection model at step S208.

[0041] Figure 3 FIG is an exemplary schematic diagram showing a portion of a blood vessel segment according to an embodiment of the present application. Figure 3 The image shown in Figure 1 shows a partial vascular segment image X. When training a detection model for vascular adhesions, binary images of corresponding individual vessel segments (e.g., segments 1-3-6; 5-2-1) can be extracted from this partial vascular segment image X. The specific binarization operation can be found in the previous section. Next, training data is constructed based on the multimodal imaging data, the individual vessel binary images, and the annotation results.

[0042] Taking vessel segment 1-3-6 as an example, if its corresponding binary image is denoted as X_binary, since vessel segment 1-3-6 is an adhesion vessel, its labeling result is 1, resulting in the training data [[X,X_binary],1]. Similarly, for vessel segment 5-2-1, which does not pass through an adhesion vessel and has a value of 0, the training data [[X,X_binary'],0] can be obtained. As previously mentioned, a single vessel can be clipped using the maximum bounding box to obtain the clipped single vessel to construct the training data [[X,X_binary_box],1]. This is then input into the detection model, encoded using an encoder, and then classified using a classifier to obtain the vascular adhesion detection results, thereby training the vascular adhesion detection model.

[0043] Figure 4FIG. 4 is an exemplary flow chart illustrating a method 400 for detecting vascular adhesion according to an embodiment of the present application. Figure 4 As shown in , the method 400 includes: step S401: acquiring multimodal image data, wherein the multimodal image data includes digital subtraction angiography data, CT angiography data, and magnetic resonance angiography data; step S402: performing vascular segmentation based on the multimodal image data to obtain a vascular map and vascular information; step S403: extracting a binary image of a single vessel based on the vascular map and vascular information; step S404: inputting the multimodal image data and the binary image of a single vessel into a trained detection model to perform vascular adhesion detection to obtain a detection result. For more details on the extraction of the binary image of a single vessel and the training of the detection model, please refer to the above Figure 1 、 Figure 2 According to the detection result, if the classification operation pred is 1, it means that there is adhesion at the middle endpoint, and other values indicate that there is no adhesion.

[0044] In some embodiments, when detecting vascular adhesions, the maximum bounding box of a single vessel can be cropped. The cropped binary image of the single vessel and the original multimodal data are then input into a trained detection model to perform vascular adhesion detection and obtain a detection result. Similarly, based on the detection result, if the classification operation pred is 1, it indicates that adhesion exists at the middle endpoint; other values indicate that adhesion does not exist.

[0045] 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 multifunctional device including various peripheral devices.

[0046] 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 can 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 can be configured to store various types of data, including various multimodal data, vascular maps and vascular information, binary maps of single blood vessels, algorithm data, intermediate results, and various programs required to run the device 500. The ROM 513 can be configured to store data and instructions required for the power-on self-test of the device 500, the initialization of various functional modules in the system, the basic input / output drivers of the system, and the booting of the operating system.

[0047] Optionally, the device 500 may also include other hardware platforms or components, such as the illustrated tensor processing unit ("TPU") 514, graphics processing unit ("GPU") 515, field programmable gate array ("FPGA") 516, and machine learning unit ("MLU") 517. It will be appreciated that while various hardware platforms or components are shown in the device 500, these are merely exemplary and non-restrictive, and those skilled in the art may add or remove corresponding hardware as needed. For example, the device 500 may include only a CPU, associated storage devices, and interface devices to implement the method for training a detection model for detecting vascular adhesions or the method for detecting vascular adhesions described herein.

[0048] 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") generation. 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, vascular maps and vascular information, and binary maps of single blood vessels.

[0049] 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 detection model for detecting vascular adhesions of the present application or to provide voice prompts and / or image video displays for detecting vascular adhesions. The input device 503 may include, for example, other input buttons or controls such as a keyboard, a mouse, a microphone, a gesture capture camera, etc., which are configured to receive audio data input 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 or MRI equipment and transmit data or results including multimodal data or various other types to the device 500.

[0050] 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.

[0051] 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.

[0052] 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 detection model for detecting vascular adhesions or detecting vascular adhesions. 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 the detection model for detecting vascular adhesion described in the present application; or realizing the method of training the detection model for detecting vascular adhesion described in the present application; Figure 4 Methods for detecting vascular adhesions are described.

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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 detection model for detecting vascular adhesions, 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 based on the multimodal image data to obtain a blood vessel map and blood vessel information; extracting a binary image of a single blood vessel according to the blood vessel map and the blood vessel information, and marking whether it passes through an adhesion vessel; constructing training data based on the multimodal imaging data, the binary image of the single blood vessel, and the annotation results; The training data is input into a detection model to perform vascular adhesion detection to obtain a detection result, so as to train the detection model for vascular adhesion detection. 2 . The method according to claim 1 , wherein the blood vessel information at least includes position information and radius information of each pixel point on the blood vessel map.

3. The method according to claim 2, wherein the binary image of the single blood vessel is extracted by the following operation: determining a target pixel point on a single blood vessel and a radius at the target pixel point according to the blood vessel map and the blood vessel information; The pixels within the radius of the target pixel point, which is centered at the target pixel point, are set as target values, and the remaining pixels are set to 0, so as to extract the binary image of the single blood vessel.

4. The method according to claim 2, further comprising: determining whether a pixel point passes through an adhesion blood vessel according to the blood vessel map and the blood vessel information; Based on the judgment result, the pixel points are marked as passing through the adhesion blood vessels and not passing through the adhesion blood vessels to obtain the marking result.

5. The method according to claim 1, further comprising: performing maximum bounding box cropping on the single blood vessel to obtain a cropped single blood vessel; The training data is constructed based on the multimodal imaging data, the cropped binary image of the single blood vessel, and the annotation results.

6. The method according to claim 1 or 5, wherein the detection model comprises an encoder and a classifier, and the training data is input into the detection model to perform vascular adhesion detection to obtain a detection result, so as to train the detection model for vascular adhesion detection: Based on the training data, using the encoder to perform an encoding operation to obtain an encoding result; The classifier is used to perform a classification operation on the encoding result to obtain a detection result of vascular adhesion detection, so as to train a detection model for vascular adhesion detection.

7. The method according to claim 6, wherein the detection model comprises a machine learning model or a deep learning model.

8. A method for detecting vascular adhesion, 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 based on the multimodal image data to obtain a blood vessel map and blood vessel information; Extracting a binary image of a single blood vessel based on the blood vessel map and the blood vessel information; and The multimodal imaging data and the binary image of the single blood vessel are input into a detection model trained according to the method of any one of claims 1 to 7 to perform vascular adhesion detection to obtain a detection result.

9. A device comprising: processor; as well as A memory storing computer instructions for training a detection model for detecting vascular adhesion, which, when executed by a processor, implement the method according to any one of claims 1 to 7; or storing computer instructions for detecting vascular adhesion, which, when executed by a processor, implement the method according to claim 8.

10. A computer-readable storage medium storing computer program instructions for training a detection model for detecting vascular adhesions, wherein the computer program instructions, when executed by one or more processors, implement the method according to any one of claims 1 to 7; or storing computer program instructions for detecting vascular adhesions, wherein the computer program instructions, when executed by one or more processors, implement the method according to claim 8.

Images