Method and system for identifying carotid artery interlayer image related to overlong styloid process

Abstract

The invention relates to the technical field of medical assistance, and discloses an overlong styloid process related carotid artery interlayer image recognition method and system, and the recognition method comprises the following steps: obtaining historical CTA image data and clinical parameters of a user; constructing a styloid process three-dimensional image by adopting a three-dimensional reconstruction technology according to the CTA image data, and constructing a graph structure based on the styloid process three-dimensional image; encoding the CTA image data, inputting the encoded CTA image data into the CNN model, and outputting the identified styloid process abnormal region and carotid artery dissection features; updating node features of the graph structure; a styloid process lesion prediction model is constructed, feature fusion is carried out on the updated node features and clinical parameters of the user and then is input into the styloid process lesion prediction model, and the styloid process lesion prediction model outputs the risk probability of the user suffering from the carotid artery dissection; according to the identification method provided by the invention, the three-dimensional reconstruction technology and the convolutional neural network model are combined, so that the overlong styloid process and the carotid artery dissection caused by the overlong styloid process can be more accurately diagnosed.

Description

Technical Field

[0001] The present invention relates to the field of medical assistance, and more specifically, to an image recognition method and system for carotid artery dissection associated with excessively long styloid process. Background Art

[0002] Carotid artery dissection caused by excessive styloid process is an important cause of stroke in young people. However, there is a lack of clinical knowledge about carotid artery dissection caused by excessive styloid process. Radiologists do not pay attention to the cause of carotid artery dissection when reporting it, which leads to repeated occurrence of carotid artery dissection caused by excessive styloid process or stent fracture after stent placement. At the same time, some patients with excessive styloid process need to turn their heads repeatedly due to the nature of their work, which inevitably leads to repeated stimulation and compression of the adjacent carotid artery, eventually leading to dissection. Therefore, early detection and prevention are crucial.

[0003] In recent years, the development of multimodal medical imaging technology and artificial intelligence methods has provided a new approach to the detection of the cause of carotid artery dissection associated with styloid process elongation. Some studies have attempted to fuse the image information of different imaging modalities and establish a carotid artery dissection cause identification and prediction model through machine learning algorithms, which has achieved preliminary results. However, existing methods lack effective multimodal image registration and fusion methods: because the association between styloid process elongation and carotid artery dissection involves complex anatomical structures, existing technologies are difficult to achieve accurate multimodal image registration and fusion, and cannot fully utilize the complementary information provided by different imaging modalities such as CT and MRI to comprehensively evaluate the styloid process and its impact on blood vessels. Summary of the invention

[0004] The present invention provides an image recognition method and system for carotid artery dissection associated with excessive styloid process, which solve the technical problems raised in the above-mentioned background technology.

[0005] The present invention provides an image recognition method for carotid artery dissection associated with excessive styloid process, comprising the following steps: Step 101, obtaining historical CTA image data and clinical parameters of the user, wherein the CTA image data includes the user's anatomical structure information, vascular condition information, pathological change information and spatial relationship information, and the clinical parameters include the user's age, gender and medical history information; Step 102, constructing a three-dimensional image of the styloid process using a three-dimensional reconstruction technology based on the CTA image data, and constructing a graph structure based on the three-dimensional image of the styloid process, wherein the nodes include carotid arteries divided at equal distances, and different carotid arteries are marked as different nodes, and a node represents a segment of a carotid artery. The condition for the existence of an edge between two nodes is that the two segments of the carotid arteries are connected; Step 103, encoding the CTA image data and inputting it into the CNN model, outputting the identified styloid process abnormal area and carotid artery dissection features, the CNN model includes a U-Net network and an output layer, and the U-Net network includes an encoder and a decoder; Step 104, updating the node features of the graph structure constructed in step 102; Step 105, constructing a styloid process lesion prediction model, fusing the updated node features and the user's clinical parameters to generate fused features, inputting the fused features into the styloid process lesion prediction model, and the styloid process lesion prediction model outputs the risk probability of the user suffering from carotid artery dissection.

[0006] In a preferred embodiment, the anatomical structure information includes: the tip position of the styloid process, the length measurement value, and the inclination and anteversion angles of the styloid process; the vascular condition information includes: the diameter of the carotid artery, the thickness of the vascular wall, and the patency of the vascular lumen; the pathological change information includes: the location, range, calcification, and plaque distribution of the arterial dissection; and the spatial relationship information includes: the distance between the styloid process and the adjacent blood vessels.

[0007] In a preferred embodiment, the method for updating node features comprises the following steps: Step 201, linearly transform all node features in the graph structure to generate a node transformation feature vector; The linear transformation is calculated as follows: ; in, represents the node transformation feature vector of node i, represents the initial feature vector of node i, represents the weight matrix; Step 202, calculating the attention coefficient between node i and node j; The calculation formula of attention coefficient is as follows: ; in, represents the attention coefficient between node i and node j, represents the node transformation feature vector of node i, represents the node transformation feature vector of node j, represents the weight matrix, represents the attention vector, represents the vector transpose, express function, Represents vector concatenation; Step 203, normalizing the attention coefficient; The calculation formula for the normalized attention coefficient is as follows: ; in, represents the normalized attention coefficient, represents the set of neighbor nodes of node i, represents the attention coefficient between node i and node j, represents the natural exponential function; Step 204, performing weighted aggregation on the features of neighbor nodes according to the normalized attention coefficient to generate updated node features; The calculation formula of weighted aggregated neighbor features is as follows: ; in, represents the updated node feature vector of node i, represents the initial eigenvector of node j, represents the ReLU activation function, represents the normalized attention coefficient, represents the set of neighbor nodes of node i, represents the weight matrix.

[0008] In a preferred embodiment, the calculation formulas for the inclination angle and anteversion angle of the styloid process are as follows: The calculation formula for the inclination angle is: ; in, represents the inclination angle of the styloid process in the coronal plane, , represents the projection vector of the styloid process on the coronal plane, , represents the reference vector, which is usually chosen to be the horizontal direction of the coronal plane; The calculation formula for the forward inclination angle is: ; in, represents the anteversion angle of the styloid process in the sagittal plane. , represents the projection vector of the styloid process on the sagittal plane, , represents the reference vector, which is usually chosen to be the horizontal direction of the sagittal plane.

[0009] In a preferred embodiment, in step 102, the node features include the three-dimensional coordinates of the carotid artery corresponding to each node, the vascular condition information of the carotid artery, the pathological change information of the carotid artery, and the spatial relationship information of the carotid artery.

[0010] In a preferred embodiment, a method for constructing a three-dimensional image of the styloid process using three-dimensional reconstruction technology based on CTA image data includes the following steps: Step 1: First, the original CTA image data is preprocessed in a standardized manner; Step 2: Recombining the original axial image in different directions through MPR technology to generate two-dimensional slice images of three viewing angles: coronal, sagittal and axial. Step 3: Based on the two-dimensional slice images of the coronal, sagittal and axial viewpoints in step 2, a three-dimensional volume rendering technology is used to generate a visualized three-dimensional image of the styloid process; Step 4: Generate continuous two-dimensional image slices of the styloid process based on the surface reconstruction technology, and obtain the user's anatomical structure information based on the generated three-dimensional image of the styloid process.

[0011] In a preferred embodiment, the fusion method of the fusion feature is to sequentially concatenate the feature vectors and clinical parameters of all nodes to form the fusion feature.

[0012] In a preferred embodiment, the calculation formula of the styloid process lesion prediction model is: ; in, represents the probability that the patient suffers from carotid artery disease, represents the Sigmoid function, represents the weight vector, represents the fusion feature, Represents the bias vector.

[0013] A diagnostic and identification system for carotid artery dissection associated with excessive styloid process, comprising the following modules: Data acquisition and preprocessing module, used to acquire and preprocess the user's CTA imaging data and clinical parameters; A three-dimensional reconstruction and graph structure building module is used to generate a visualized three-dimensional image of the styloid process according to the three-dimensional reconstruction technology and to build a graph structure based on the image; CNN model feature extraction module, used to automatically identify and extract key features from CTA image data; The graph structure update module is used to update the node features in the graph structure according to the output results of the CNN model; The fusion and risk assessment module fuses the updated node features with the user's clinical parameters, inputs them into the styloid process lesion prediction model, and outputs the risk probability.

[0014] A storage medium stores non-transitory computer-readable instructions. When the non-transitory computer-readable instructions are executed by a computer, the steps in the above-mentioned method for image recognition of carotid artery dissection associated with excessive styloid process can be executed.

[0015] The beneficial effects of the present invention are: The recognition method of the present invention can more accurately measure geometric parameters such as the length and angle of the styloid process and the distance between the tip of the styloid process and the adjacent blood vessels by combining the three-dimensional reconstruction technology and the convolutional neural network model. These detailed anatomical structure information provides doctors with an intuitive view, which helps to more accurately diagnose the excessive length of the styloid process and the carotid artery dissection caused by it. The present invention constructs a more comprehensive prediction model for styloid process lesions by combining the image features extracted by CNN with the geometric parameters obtained by three-dimensional reconstruction. The integration of multiple information sources makes the final output risk probability more reliable, providing strong support for clinical decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of the imaging identification method of the present invention for carotid artery dissection associated with excessive styloid process.

[0017] Figure 2 It is a flow chart of a method for updating node features in the identification method of the present invention.

[0018] Figure 3 It is a block diagram of the image recognition system for carotid artery dissection associated with excessive styloid process of the present invention. DETAILED DESCRIPTION

[0019] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the contents of this specification. Each example may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0020] like Figure 1 As shown, a method for image recognition of carotid artery dissection associated with excessive styloid process comprises the following steps: Step 101, obtaining historical CTA image data and clinical parameters of the user, wherein the CTA image data includes the user's anatomical structure information, vascular condition information, pathological change information and spatial relationship information, and the clinical parameters include the user's age, gender and medical history information; It should be noted that the CTA image data are obtained from the CTA images of the coronary, sagittal and axial viewpoints obtained by the patient in the hospital using the coronary CTA technology; that is, the CTA image data also includes the axial image, among which the CTA images of the coronary, sagittal and axial viewpoints are obtained from the axial image; finally, Gaussian filtering is used to remove noise, and the histogram equalization preprocessing method is used to process the user's historical CTA image data and clinical parameters.

[0021] In one embodiment of the present invention, the anatomical structure information includes: the tip position of the styloid process, the length measurement value, and the medial and anteversion angles of the styloid process; In one embodiment of the present invention, the calculation formula of the styloid process length is as follows: ; in, represents the length of the styloid process, and represent the coordinates of the starting point and midpoint of the styloid process, respectively; In one embodiment of the present invention, the distance from the tip of the styloid process to the center of the adjacent carotid artery is calculated as follows: ; in, represents the minimum Euclidean distance from the tip of the styloid process to the center of the adjacent carotid artery, represents the three-dimensional coordinate vector of the styloid process tip, Represents the three-dimensional coordinate vector of the point near the center of the carotid artery, represents the minimum function; In one embodiment of the present invention, the calculation formulas for the inclination angle and the anteversion angle of the styloid process are as follows: The calculation formula for the inclination angle is: ; in, represents the inclination angle of the styloid process in the coronal plane, , represents the projection vector of the styloid process on the coronal plane, , represents the reference vector, which is usually chosen to be the horizontal direction of the coronal plane; The calculation formula for the forward inclination angle is: ; in, represents the anteversion angle of the styloid process in the sagittal plane. , represents the projection vector of the styloid process on the sagittal plane, , represents the reference vector, which is usually chosen to be the horizontal direction of the sagittal plane; The location and morphology of the carotid artery include the path, bifurcation location and morphological characteristics of the internal and external carotid arteries; In one embodiment of the present invention, the vascular condition information includes: the diameter of the carotid artery, the thickness of the vascular wall, and the patency of the vascular lumen; Carotid artery diameter: The diameter of the carotid artery is measured in equally spaced segments to assess whether stenosis or dilation is present. Blood vessel wall thickness: by measuring the thickness of the intima-media of the carotid artery wall, especially the thickness of the intima-media, it is mainly used to evaluate atherosclerosis; Vessel patency: Checks whether there is plaque formation or other abnormalities that hinder blood flow in the vessel lumen (expressed as a percentage); In one embodiment of the present invention, the pathological change information includes: the location, range, calcification, plaque distribution, etc. of the arterial dissection; Calcification of arterial dissection: Detection of calcification points in the blood vessel wall, as calcification is one of the hallmarks of arteriosclerosis; Plaque distribution: Detailed record of the location, size, morphology (softness or hardness of plaques, such as soft plaques, hard plaques, etc.) of plaques and their effects on vascular flow dynamics; In one embodiment of the present invention, the spatial relationship information includes: the distance between the styloid process and the adjacent blood vessel; Distance between the styloid process and adjacent blood vessels: the distance from the tip of the styloid process to the center of the nearest carotid artery.

[0022] Step 102, constructing a three-dimensional image of the styloid process using a three-dimensional reconstruction technology based on the CTA image data, and constructing a graph structure based on the three-dimensional image of the styloid process, wherein the nodes include carotid arteries divided at equal distances, and different carotid arteries are marked as different nodes, and a node represents a segment of a carotid artery. The condition for the existence of an edge between two nodes is that the two segments of the carotid arteries are connected; The node features include the three-dimensional coordinates of the carotid artery corresponding to each node, the vascular condition information of the carotid artery, the pathological change information of the carotid artery, and the spatial relationship information of the carotid artery; It should be noted that the three-dimensional coordinates of the carotid artery corresponding to each node are the coordinates of the center point of the segment of the carotid artery, and the vascular condition information of the carotid artery includes the diameter of the carotid artery, the vascular wall thickness of the carotid artery, and the vascular lumen patency of the carotid artery, wherein the diameter of the carotid artery is the average arterial diameter of the segment where each node is located, the vascular wall thickness of the carotid artery is the average arterial wall thickness of the segment where each node is located, and the vascular lumen patency of the carotid artery is the original value obtained from the CTA imaging data; the pathological change information of the carotid artery includes the location, range, calcification, and plaque distribution of the arterial dissection, wherein the calcification and plaque distribution are represented by 0 or 1, and the location and range of the arterial dissection are represented by the midpoint coordinates and area numerical size of the arterial dissection, respectively; the spatial relationship information of the carotid artery includes the distance between the styloid process and the adjacent blood vessels and the spatial configuration at the vascular bifurcation, wherein the distance between the styloid process and the adjacent blood vessels and the spatial configuration at the vascular bifurcation are both represented by the information obtained from the CTA imaging data.

[0023] In one embodiment of the present invention, the node features are encoded using one-hot encoding and concatenated in sequence; In one embodiment of the present invention, a method for constructing a three-dimensional image of the styloid process using three-dimensional reconstruction technology based on CTA image data includes the following steps: Step 1: First, the original CTA image data is preprocessed in a standardized manner; It should be noted that the standardized preprocessing of raw CTA image data includes operations such as denoising and contrast enhancement to improve image quality and make subsequent analysis more accurate; Step 2: Recombining the original axial image in different directions through MPR technology to generate two-dimensional slice images of three viewing angles: coronal, sagittal and axial. Multiplanar reconstruction involves reconstructing the original axial image into two-dimensional slices from different perspectives. The specific steps are as follows: Coronal section: Cut along the anterior-posterior direction to generate a series of two-dimensional slices parallel to the anterior-posterior direction; Sagittal: Cut along the left-right direction to generate a series of two-dimensional slices parallel to the left-right direction; Axial: Cut along the up-down direction to generate a series of two-dimensional slices parallel to the ground; It should be noted that MPR technology is a multi-planar reconstruction technology. MPR is a technology that generates two-dimensional slice images of multiple perspectives such as coronal, sagittal and axial positions by recombining the original axial image in different directions; Coronal: Scans perpendicular to the front-to-back direction, from the front of the head to the back, showing the left and right structures; Sagittal: perpendicular to the left and right directions, viewed from the side, showing the anterior and posterior structures; Axial view: Parallel to the ground, scanning from the top of the head downward, showing the upper and lower structures.

[0024] Step 3: Based on the two-dimensional slice images of the coronal, sagittal and axial viewpoints in step 2, a three-dimensional volume rendering technology is used to generate a visualized three-dimensional image of the styloid process; 3D volume rendering is achieved by combining multiple 2D slices into a complete 3D model. The basic steps are as follows: Data preparation: Obtain preprocessed CTA image data; Volume rendering: Converting 2D slice data into 3D stereoscopic views using volume rendering algorithms such as ray casting; Step 4: Generate continuous two-dimensional image slices of the styloid process based on the surface reconstruction technology, and obtain the user's anatomical structure information based on the generated three-dimensional image of the styloid process.

[0025] The identification method of the present invention uses three-dimensional reconstruction technology to provide a more intuitive anatomical structure view, helping doctors to better understand the specific location of the lesion, its morphology and its relationship with surrounding tissues. This visualization helps doctors make more accurate diagnoses. In addition, through three-dimensional reconstruction, geometric parameters such as the length and angle of the styloid process (such as inclination and anteversion), and the distance between the tip of the styloid process and adjacent blood vessels can be measured more accurately. These parameters are crucial for evaluating the impact of excessive styloid process on the carotid artery. If surgical intervention is required, the detailed information provided by three-dimensional reconstruction can help surgeons develop a more accurate surgical plan.

[0026] Surface reconstruction technology can generate continuous two-dimensional slices along the surface of the anatomical structure of interest. The specific steps are as follows: Define Path: Select a path along the structure of interest (e.g., styloid process).

[0027] Generate Slices: Generates a series of consecutive 2D slices along the path, with each slice representing a cross section of the structure.

[0028] Step 103, encoding the CTA image data and inputting it into the CNN model, outputting the identified styloid process abnormal area and carotid artery dissection features, the CNN model includes a U-Net network and an output layer, the U-Net network includes an encoder and a decoder, the loss function of the CNN model is a binary cross entropy loss, and an Adam optimizer is used; Step 104, updating the node features of the graph structure constructed in step 102; In one embodiment of the present invention, Figure 2 As shown, the method for updating node features includes the following steps: Step 201, linearly transform all node features in the graph structure to generate a node transformation feature vector; The linear transformation is calculated as follows: ; in, represents the node transformation feature vector of node i, represents the initial feature vector of node i, represents the weight matrix; Step 202, calculating the attention coefficient between node i and node j; The calculation formula of attention coefficient is as follows: ; in, represents the attention coefficient between node i and node j, represents the node transformation feature vector of node i, represents the node transformation feature vector of node j, represents the weight matrix, represents the attention vector, represents the vector transpose, express function, Represents vector concatenation; Step 203, normalizing the attention coefficient; The calculation formula for the normalized attention coefficient is as follows: ; in, represents the normalized attention coefficient, represents the set of neighbor nodes of node i, represents the attention coefficient between node i and node j, represents the natural exponential function; Step 204, performing weighted aggregation on the features of neighbor nodes according to the normalized attention coefficient to generate updated node features; The calculation formula of weighted aggregated neighbor features is as follows: ; in, represents the updated node feature vector of node i, represents the initial eigenvector of node j, represents the ReLU activation function, represents the normalized attention coefficient, represents the set of neighbor nodes of node i, represents the weight matrix.

[0029] Step 105, constructing a styloid process lesion prediction model, fusing the updated node features and the user's clinical parameters to generate fusion features, inputting the fusion features into the styloid process lesion prediction model, and the styloid process lesion prediction model outputs the risk probability of the user suffering from carotid artery dissection; In one embodiment of the present invention, the calculation formula of the styloid process lesion prediction model is: ; in, represents the probability that the patient suffers from carotid artery disease, represents the Sigmoid function, represents the weight vector, represents the fusion feature, represents the bias vector; In one embodiment of the present invention, the method for generating fusion features after feature fusion of updated node features and user's clinical parameters adopts the method of splicing the feature vectors and clinical parameters of all nodes together to form a new feature vector; For example, all node feature vectors updated in step 104 are ,in, Indicates the number of nodes; sets the user's clinical parameters to be encoded to form a feature vector , then the fusion feature is: .

[0030] The present invention automatically identifies and extracts key features by designing a CNN model, and can automatically learn and extract key features, such as styloid process abnormalities and carotid artery dissection, from a large amount of CTA image data, which greatly reduces the workload of manual annotation and improves the processing speed; through three-dimensional reconstruction, geometric parameters such as styloid process length, angles (such as inclination and anteversion), and the distance between the tip of the styloid process and adjacent blood vessels can be measured more accurately, which can assist doctors in making more accurate diagnosis and treatment decisions, especially in complex cases. The present invention can provide more comprehensive information by combining the features extracted by CNN with the geometric parameters of three-dimensional reconstruction, thereby improving the accuracy of risk assessment, and combining multiple information sources to establish a more powerful prediction model, making the final risk probability more reliable.

[0031] By combining CNN and 3D reconstruction, the present invention can fully utilize the advantages of both to achieve efficient and accurate key feature recognition and extraction, while providing intuitive anatomical structure views and precise geometric parameter measurements. This method not only improves the accuracy of diagnosis, but also integrates multi-dimensional information to ultimately construct a styloid process lesion prediction model that can output a more reliable risk probability, providing strong support for clinical decision-making.

[0032] In one embodiment of the present invention, Figure 3 As shown, a diagnosis and identification system for carotid artery dissection associated with excessive styloid process includes the following modules: Data acquisition and preprocessing module, used to acquire and preprocess the user's CTA imaging data and clinical parameters; It should be noted that the user's historical CTA image data (including anatomical structure information, vascular condition information, pathological change information and spatial relationship information) and clinical parameters (such as age, gender, medical history, etc.) are obtained; the original CTA image data is subjected to standardized preprocessing (denoising, contrast enhancement, etc.), and two-dimensional slice images of three perspectives, namely, coronal, sagittal and axial, are generated; A three-dimensional reconstruction and graph structure building module is used to generate a visualized three-dimensional image of the styloid process according to the three-dimensional reconstruction technology and to build a graph structure based on the image; It should be noted that the three-dimensional image of the styloid process is generated using MPR technology and three-dimensional volume rendering technology; based on the generated three-dimensional image, the geometric parameters such as the length, inclination angle, anteversion angle of the styloid process and the distance from the tip of the styloid process to the center of the adjacent carotid artery are calculated; a graph structure is constructed, with nodes representing different sections of the carotid artery and edges representing the connection relationship between adjacent carotid artery sections. Each node contains the corresponding three-dimensional coordinates of the carotid artery, vascular condition information, pathological change information and spatial relationship information; CNN model feature extraction module, used to automatically identify and extract key features from CTA image data; It should be noted that the pre-processed CTA image data is input into a CNN model (such as a U-Net network) to output the identified styloid abnormality area and carotid artery dissection features; The loss function uses binary cross entropy loss, and the optimizer uses Adam optimizer; The graph structure update module is used to update the node features in the graph structure according to the output results of the CNN model; It should be noted that all node features are linearly transformed to generate node transformation feature vectors; the attention coefficients between nodes are calculated and normalized; the features of neighboring nodes are weighted and aggregated according to the normalized attention coefficients to generate updated node features; The fusion and risk assessment module fuses the updated node features with the user's clinical parameters, inputs them into the styloid process lesion prediction model, and outputs the risk probability.

[0033] It should be noted that the feature vectors of all nodes and the user's clinical parameters are spliced ​​together to form a new feature vector; the fused features are input into the styloid process lesion prediction model to calculate the patient's risk probability of carotid artery dissection; It should be further explained that an output and decision support module may be connected after the fusion and risk assessment module to provide the final risk assessment results and assist doctors in making diagnosis and treatment decisions; For example, the patient's risk of carotid artery dissection can be output, and a detailed anatomical view and geometric parameter measurements can be provided to help doctors develop more precise surgical plans or preventive measures.

[0034] Through the modular system design, the present invention can effectively realize the full process automation from data acquisition to final risk assessment, improve the diagnostic efficiency and accuracy, and provide strong support for clinical practice.

[0035] A storage medium stores non-transitory computer-readable instructions. When the non-transitory computer-readable instructions are executed by a computer, the steps in the above-mentioned method for image recognition of carotid artery dissection associated with excessive styloid process can be executed.

[0036] The above describes an embodiment of the present embodiment, but the present embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present embodiment, ordinary technicians in this field can also make many forms, all of which are within the protection of the present embodiment.

Claims

1. A method for image recognition of carotid artery dissection associated with excessive styloid process, characterized in that: The following steps are involved: Step 101, obtaining historical CTA image data and clinical parameters of the user, wherein the CTA image data includes the user's anatomical structure information, vascular condition information, pathological change information and spatial relationship information, and the clinical parameters include the user's age, gender and medical history information; Step 102, constructing a three-dimensional image of the styloid process using a three-dimensional reconstruction technology based on the CTA image data, and constructing a graph structure based on the three-dimensional image of the styloid process, wherein the nodes include carotid arteries divided at equal distances, and different carotid arteries are marked as different nodes, and a node represents a segment of a carotid artery. The condition for the existence of an edge between two nodes is that the two segments of the carotid arteries are connected; Step 103, encoding the CTA image data and inputting it into the CNN model, outputting the identified styloid process abnormal area and carotid artery dissection features, the CNN model includes a U-Net network and an output layer, and the U-Net network includes an encoder and a decoder; Step 104, updating the node features of the graph structure constructed in step 102; Step 105, constructing a styloid process lesion prediction model, fusing the updated node features and the user's clinical parameters to generate fused features, inputting the fused features into the styloid process lesion prediction model, and the styloid process lesion prediction model outputs the risk probability of the user suffering from carotid artery dissection.

2. The method for image recognition of carotid artery dissection associated with excessive styloid process according to claim 1, characterized in that: The anatomical structure information includes: the tip position of the styloid process, the length measurement value, and the inclination and anteversion angles of the styloid process; the vascular condition information includes: the diameter of the carotid artery, the thickness of the vascular wall, and the patency of the vascular lumen; the pathological change information includes: the location, range, calcification, and plaque distribution of the arterial dissection; the spatial relationship information includes: the distance between the styloid process and the adjacent blood vessels.

3. The method for image recognition of carotid artery dissection associated with excessive styloid process according to claim 2, characterized in that: The method for updating node features comprises the following steps: Step 201, linearly transform all node features in the graph structure to generate a node transformation feature vector; The linear transformation is calculated as follows: ； in, represents the node transformation feature vector of node i, represents the initial feature vector of node i, represents the weight matrix; Step 202, calculating the attention coefficient between node i and node j; The calculation formula of attention coefficient is as follows: ； in, represents the attention coefficient between node i and node j, represents the node transformation feature vector of node i, represents the node transformation feature vector of node j, represents the weight matrix, represents the attention vector, represents the vector transpose, express function, Represents vector concatenation; Step 203, normalizing the attention coefficient; The calculation formula for the normalized attention coefficient is as follows: ； in, represents the normalized attention coefficient, represents the set of neighbor nodes of node i, represents the attention coefficient between node i and node j, represents the natural exponential function; Step 204, performing weighted aggregation on the features of neighbor nodes according to the normalized attention coefficient to generate updated node features; The calculation formula of weighted aggregated neighbor features is as follows: ； in, represents the updated node feature vector of node i, represents the initial eigenvector of node j, represents the ReLU activation function, represents the normalized attention coefficient, represents the set of neighbor nodes of node i, represents the weight matrix.

4. The method for image recognition of carotid artery dissection associated with excessive styloid process according to claim 3, characterized in that: The calculation formulas for the medial and anteversion angles of the styloid process are as follows: The calculation formula for the inclination angle is: ； in, represents the inclination angle of the styloid process in the coronal plane, , represents the projection vector of the styloid process on the coronal plane, , represents the reference vector, which is usually chosen to be the horizontal direction of the coronal plane; The calculation formula for the forward inclination angle is: ； in, represents the anteversion angle of the styloid process in the sagittal plane. , represents the projection vector of the styloid process on the sagittal plane, , represents the reference vector, which is usually chosen to be the horizontal direction of the sagittal plane.

5. The method for image recognition of carotid artery dissection associated with excessive styloid process according to claim 4, characterized in that: In step 102, the node features include the three-dimensional coordinates of the carotid artery corresponding to each node, the vascular condition information of the carotid artery, the pathological change information of the carotid artery, and the spatial relationship information of the carotid artery.

6. The method for image recognition of carotid artery dissection associated with excessive styloid process according to claim 5, characterized in that: The method for constructing a three-dimensional image of the styloid process using three-dimensional reconstruction technology based on CTA image data includes the following steps: Step 1: First, the original CTA image data is preprocessed in a standardized manner; Step 2: Recombining the original axial image in different directions through MPR technology to generate two-dimensional slice images of three viewing angles: coronal, sagittal and axial. Step 3: Based on the two-dimensional slice images of the coronal, sagittal and axial viewpoints in step 2, a three-dimensional volume rendering technology is used to generate a visualized three-dimensional image of the styloid process; Step 4: Generate continuous two-dimensional image slices of the styloid process based on the surface reconstruction technology, and obtain the user's anatomical structure information based on the generated three-dimensional image of the styloid process.

7. The method for image recognition of carotid artery dissection associated with excessive styloid process according to claim 6, characterized in that: The fusion method of fusion features is to sequentially concatenate the feature vectors and clinical parameters of all nodes to form fusion features.

8. The method for image recognition of carotid artery dissection associated with excessive styloid process according to claim 7, characterized in that: The calculation formula of the styloid process lesion prediction model is: ； in, represents the probability that the patient suffers from carotid artery disease, represents the Sigmoid function, represents the weight vector, represents the fusion feature, Represents the bias vector.

9. A system for image recognition of carotid artery dissection associated with excessive styloid process, used to execute the method for image recognition of carotid artery dissection associated with excessive styloid process as claimed in any one of claims 1 to 8, characterized in that: Includes the following modules: Data acquisition and preprocessing module, used to acquire and preprocess the user's CTA imaging data and clinical parameters; A three-dimensional reconstruction and graph structure building module is used to generate a visualized three-dimensional image of the styloid process according to the three-dimensional reconstruction technology and to build a graph structure based on the image; CNN model feature extraction module, used to automatically identify and extract key features from CTA image data; The graph structure update module is used to update the node features in the graph structure according to the output results of the CNN model; The fusion and risk assessment module fuses the updated node features with the user's clinical parameters, inputs them into the styloid process lesion prediction model, and outputs the risk probability.

10. A storage medium, characterized in that: It stores non-transitory computer-readable instructions, and when the non-transitory computer-readable instructions are executed by a computer, the steps in the image recognition method for carotid artery dissection associated with excessive styloid process as described in claim 8 can be executed.

Images