Ultrasonic carotid plaque type identification method and system and storage medium

Abstract

The invention relates to an ultrasonic carotid plaque type identification method and system and a storage medium, and the method comprises the following steps: respectively obtaining a neck ultrasonic image and carotid artery mechanical data before and after the extrusion of a carotid artery extrusion belt on a carotid artery, and carrying out the preprocessing; image reconstruction is carried out based on the neck ultrasonic image, probability statistics is carried out on a suspected plaque area in the reconstructed image, and the position and the form of a plaque are identified; the mechanical response of the carotid artery in the extrusion process is analyzed based on the carotid artery mechanical data; and inputting the identified position and form of the plaque and the mechanical response into the soft and hard plaque judgment model, and outputting a plaque type identification result. Compared with the prior art, the method has the advantages that an accurate carotid plaque type judgment result can be obtained, and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to an ultrasonic carotid artery plaque type recognition method, system and storage medium. Background Art

[0002] With the rapid development and widespread application of ultrasound medicine, ultrasound technology, especially B-mode ultrasound examination, referred to as B-ultrasound, plays an important role in modern medicine. B-ultrasound can clearly display various cross-sectional images of various organs and surrounding organs, and the images are close to the real anatomical structure. Therefore, it is widely used in the diagnosis of various diseases such as cardiology, gastroenterology, urology, and obstetrics and gynecology.

[0003] As a branch of ultrasound technology, neck vascular ultrasound uses ultrasound beams to scan the human body and obtain images of neck blood vessels by receiving and processing reflected signals. This method can evaluate the shape, intima-media thickness, lumen size, blood flow, etc. of neck blood vessels such as the carotid artery, vertebral artery, subclavian artery, internal and external jugular veins, so as to determine the relevant lesions of neck blood vessels. Neck vascular ultrasound is simple, fast, low-cost, and radiation-free, and is an important means to evaluate the health of neck blood vessels. However, traditional carotid artery screening mainly analyzes ultrasound images to obtain plaque information, and cannot accurately determine whether the plaque type is hard or soft, which adds uncertainty to the subsequent treatment process.

[0004] In summary, the inability of traditional carotid artery screening methods to accurately determine the softness or hardness type of plaques has become a problem that technicians in this field urgently need to solve. Summary of the invention

[0005] The purpose of the present invention is to provide an ultrasonic carotid plaque type identification method, system and storage medium, which can accurately obtain the carotid plaque type by combining a carotid compression band with an ultrasonic probe, a soft and hard plaque judgment model and mechanical analysis.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A method for identifying carotid artery plaque types using ultrasound, comprising the following steps:

[0008] Acquire the neck ultrasound image and carotid artery mechanical data before and after the carotid artery is squeezed by the carotid artery squeeze band, and perform preprocessing;

[0009] Image reconstruction is performed based on the ultrasound image of the neck, and probability statistics are performed on the areas suspected of plaques in the reconstructed image to identify the location and morphology of the plaques;

[0010] Analyze the mechanical response of the carotid artery during compression based on the carotid artery mechanical data;

[0011] The position, morphology and mechanical response of the identified plaque are input into the soft and hard plaque judgment model, and the soft and hard type identification results of the plaque are output.

[0012] The mechanical response includes the elasticity of the blood vessel wall, blood flow velocity and hemodynamic state, wherein the elasticity of the blood vessel wall is evaluated by monitoring the diameter change and recovery speed of the carotid artery during the squeezing process; the blood flow pattern in the plaque area is analyzed by monitoring the changes in blood flow velocity and flow direction during the squeezing process; and the hemodynamic state of the entire carotid artery is evaluated by combining the elasticity of the blood vessel wall and the blood flow velocity data.

[0013] The flow patterns include eddy flow, turbulence, slowed flow, uneven flow and reverse flow.

[0014] The hemodynamic state includes pressure gradient and blood flow resistance.

[0015] The image reconstruction based on the neck ultrasound image specifically includes: using an edge detection algorithm to identify the blood vessel boundaries in the neck ultrasound image, using a texture analysis algorithm to analyze plaque features, and refining image information through morphological operations to obtain a reconstructed image.

[0016] The soft and hard plaque judgment model is a classification model based on machine learning. The classification model is trained by binding data pairs of ultrasound images of neck plaques before and after the application of the carotid artery compression band, carotid artery mechanical data and laboratory hardness test data corresponding to the neck plaques, and the model is updated and trained according to the newly collected data during the detection process.

[0017] The classification model is constructed based on one of a vector machine, a random forest or a deep learning network.

[0018] An ultrasonic carotid artery plaque type identification system is used to implement the above method, the system comprising:

[0019] A carotid artery compression band is used to apply compression to the carotid artery and obtain mechanical data of the carotid artery before and after the compression;

[0020] Ultrasound probe to obtain ultrasound images of the neck before and after compression of the carotid artery

[0021] A signal processing module, used for preprocessing the neck ultrasound image;

[0022] An image analysis module is used to reconstruct an image based on the neck ultrasound image, perform probability statistics on the area suspected of plaque in the reconstructed image, and identify the location and morphology of the plaque;

[0023] Mechanical analysis module, used to analyze the mechanical response of the carotid artery during compression based on the carotid artery mechanical data;

[0024] The soft and hard plaque judgment module is used to input the position, morphology and mechanical response of the identified plaque into the soft and hard plaque judgment model, and output the soft and hard type identification result of the plaque.

[0025] The system also includes an interactive module, including a user interactive interface, for displaying ultrasound images, plaque hardness and softness type judgment results and health advice, and providing a data export function.

[0026] A storage medium stores a program, which implements the method described above when executed.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The present invention uses a carotid artery compression band to fix the patient's neck during the detection process and slightly compress the carotid artery to help obtain clearer ultrasound images. At the same time, it monitors the mechanical response of the blood vessels under compression, and then uses the soft and hard plaque judgment model to automatically and accurately judge the type of plaque, avoiding the subjectivity and uncertainty of human judgment and improving the accuracy and reliability of diagnosis.

[0029] 2. The soft and hard plaque judgment model of the present invention is based on machine learning such as vector machines, random forests or deep learning networks, which can automatically analyze the output results of the image analysis module and judge the soft and hard types of plaques. The soft and hard plaque judgment model is continuously optimized through training with a large amount of known data, and can be updated with newly collected data to improve the accuracy of judgment.

[0030] 3. The present invention monitors the diameter change, recovery speed, blood flow rate and other mechanical responses of the carotid artery during the compression process, and combines these data to evaluate the elasticity and hardness of the blood vessel wall, analyze the blood flow pattern, and further evaluate the hemodynamic state of the entire carotid artery system. The monitored elasticity and hardness of the blood vessel wall, blood flow rate and hemodynamic state are used as partial features to determine the type of plaque, which improves the accuracy of the determination of the plaque type, and the mechanical response can also be output as an analysis result, thereby providing a comprehensive assessment of the health of the carotid artery.

[0031] 4. The present invention uses image processing algorithms such as edge detection, texture analysis and morphological operations to reconstruct the processed signals so as to more clearly display the structure and plaque of the carotid artery. The entire detection process is non-invasive and safe, and the patient experience is good and easy to accept, which helps to achieve early screening and intervention of carotid artery disease.

[0032] 5. The interactive module of the present invention provides an intuitive user interface to display ultrasound images, plaque type judgment results and health advice, and has a data export function to facilitate doctors to conduct subsequent analysis and patient management. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 is a flow chart of the method of the present invention;

[0034] Figure 2 It is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0035] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0036] Example 1

[0037] This embodiment provides a method for identifying carotid artery plaque types by ultrasound. Figure 1 As shown, the following steps are included:

[0038] S1, respectively obtaining neck ultrasound images and carotid artery mechanical data before and after the carotid artery is squeezed by a carotid artery compression band, and performing preprocessing.

[0039] S2, image reconstruction is performed based on the neck ultrasound image, and probability statistics are performed on the area suspected of plaque in the reconstructed image to identify the location and morphology of the plaque.

[0040] In this embodiment, an edge detection algorithm is used to identify blood vessel boundaries in the neck ultrasound image, a texture analysis algorithm is used to analyze plaque features, and image information is refined through morphological operations to obtain a reconstructed image.

[0041] S3, analysis of the mechanical response of the carotid artery during compression based on carotid artery mechanical data.

[0042] Mechanical responses include the elasticity of the blood vessel wall, blood flow velocity and hemodynamic state. The elasticity of the blood vessel wall is evaluated by monitoring the diameter change and recovery speed of the carotid artery during squeezing. The flow pattern of blood in the plaque area is analyzed by monitoring the changes in blood flow velocity and flow direction during squeezing. The flow pattern includes eddy current, turbulence, slowed flow, uneven flow and reverse flow. The hemodynamic state of the entire carotid artery is evaluated by combining the elasticity of the blood vessel wall and blood flow velocity data. The hemodynamic state includes pressure gradient and blood flow resistance.

[0043] S4, inputting the position, morphology and mechanical response of the identified plaque into the soft and hard plaque judgment model, and outputting the soft and hard type identification result of the plaque.

[0044] The soft and hard plaque judgment model is a classification model based on machine learning. The classification model is trained by binding data pairs of ultrasound images of neck plaques before and after the application of the carotid artery compression band, carotid artery mechanical data and laboratory hardness test data corresponding to the neck plaques, and the model is updated and trained according to the newly collected data during the detection process.

[0045] In this embodiment, the classification model is constructed based on one of a vector machine, a random forest or a deep learning network.

[0046] Example 2

[0047] This embodiment provides an ultrasonic carotid artery plaque type identification system for implementing the method described in the above embodiment 1, the system comprising:

[0048] Carotid artery compression band, used to help fix the patient's neck and slightly compress the carotid artery during the test, and obtain the carotid artery mechanical data before and after the compression;

[0049] An ultrasound probe for obtaining ultrasound images of the neck before and after compression of the carotid artery;

[0050] A signal processing module, used for preprocessing the neck ultrasound image;

[0051] An image analysis module is used to reconstruct an image based on the neck ultrasound image, perform probability statistics on the area suspected of plaque in the reconstructed image, and identify the location and morphology of the plaque;

[0052] Mechanical analysis module, used to analyze the mechanical response of the carotid artery during compression based on the carotid artery mechanical data;

[0053] The soft and hard plaque judgment module is used to input the position, morphology and mechanical response of the identified plaque into the soft and hard plaque judgment model, and output the soft and hard type identification result of the plaque.

[0054] The system also includes an interactive module, including a user interactive interface, for displaying ultrasound images, plaque hardness and softness type judgment results and health advice, and providing a data export function.

[0055] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0056] In one embodiment, the implementation process of the above system is:

[0057] The patient lies flat on the examination bed with the head slightly tilted to one side to expose the neck area so that the ultrasound probe can fully contact and scan the carotid artery. Select a suitable probe frequency, such as a 5-12MHz linear array probe or a small micro-convex probe, to ensure that the structure of the carotid artery can be clearly displayed. Prepare a carotid artery compression band and adjust it to an appropriate tightness to assist in fixing the patient's neck and slightly compressing the carotid artery during the test. Turn on the ultrasound carotid plaque type identification system to ensure that each module is operating normally.

[0058] Use an ultrasound probe to scan the patient's neck horizontally and vertically to obtain a two-dimensional ultrasound image of the carotid artery. Pay attention to scanning key areas such as the common carotid artery, internal carotid artery, external carotid artery, and vertebral artery to ensure that the image is clear and complete.

[0059] The signal processing module processes the signals collected by the ultrasound probe, including filtering, amplification and other steps, to improve the image quality.

[0060] The signal processed by the signal processing module is transmitted to the image analysis module for image reconstruction. The image analysis module uses edge detection algorithms to identify vascular boundaries, texture analysis algorithms to analyze plaque features, and morphological operations to further refine image information. The probability statistics unit in the image analysis module performs probability statistics on the suspected plaque areas in the image to identify the specific location and morphology of the plaque.

[0061] The carotid artery compression band works continuously during the test. The mechanical analysis module monitors the diameter change and recovery speed of the carotid artery during the compression process, and evaluates the elasticity and hardness of the blood vessel wall. At the same time, by monitoring the changes in blood flow rate, the blood flow pattern in the plaque area is analyzed, such as whether there are eddies, turbulence, slow flow rate, etc. The mechanical analysis module combines these data to evaluate the hemodynamic state of the entire carotid artery system, including pressure gradient and blood flow resistance.

[0062] The soft and hard plaque judgment module receives the output results of the image analysis module and the mechanical analysis module, and uses a machine learning-based classification algorithm such as a deep learning network to judge the soft and hard types of plaques.

[0063] The soft and hard plaque judgment model judges whether the patient's plaque is soft or hard, and this result is displayed to medical staff through the user interaction interface. The system displays clear ultrasound images to medical staff through the user interaction interface and marks the location and size of the plaque. Medical staff can export all the data of this screening, including ultrasound images, plaque type judgment results, hemodynamic analysis results, etc., into electronic reports through the data export function of the interactive module.

[0064] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0065] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning, or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. A method for identifying carotid artery plaque types using ultrasound, characterized in that: The following steps are involved: Acquire the neck ultrasound image and carotid artery mechanical data before and after the carotid artery is squeezed by the carotid artery squeeze band, and perform preprocessing; Image reconstruction is performed based on the ultrasound image of the neck, and probability statistics are performed on the areas suspected of plaques in the reconstructed image to identify the location and morphology of the plaques; Analyze the mechanical response of the carotid artery during compression based on the carotid artery mechanical data; The position, morphology and mechanical response of the identified plaque are input into the soft and hard plaque judgment model, and the soft and hard type identification results of the plaque are output.

2. The method for identifying carotid artery plaque types by ultrasound according to claim 1, characterized in that: The mechanical response includes the elasticity of the blood vessel wall, blood flow velocity and hemodynamic state, wherein the elasticity of the blood vessel wall is evaluated by monitoring the diameter change and recovery speed of the carotid artery during the squeezing process; the blood flow pattern in the plaque area is analyzed by monitoring the changes in blood flow velocity and flow direction during the squeezing process; and the hemodynamic state of the entire carotid artery is evaluated by combining the elasticity of the blood vessel wall and the blood flow velocity data.

3. The method for identifying carotid artery plaque types by ultrasound according to claim 2, characterized in that: The flow patterns include eddy flow, turbulence, slowed flow, uneven flow and reverse flow.

4. The method for identifying carotid artery plaque types by ultrasound according to claim 2, characterized in that: The hemodynamic state includes pressure gradient and blood flow resistance.

5. The method for identifying carotid artery plaque types by ultrasound according to claim 1, characterized in that: The image reconstruction based on the neck ultrasound image specifically includes: using an edge detection algorithm to identify the blood vessel boundaries in the neck ultrasound image, using a texture analysis algorithm to analyze plaque features, and refining image information through morphological operations to obtain a reconstructed image.

6. The method for identifying carotid artery plaque types by ultrasound according to claim 1, characterized in that: The soft and hard plaque judgment model is a classification model based on machine learning. The classification model is trained by binding data pairs of ultrasound images of neck plaques before and after the application of the carotid artery compression band, carotid artery mechanical data and laboratory hardness test data corresponding to the neck plaques, and the model is updated and trained according to the newly collected data during the detection process.

7. The method for identifying carotid artery plaque types by ultrasound according to claim 6, characterized in that: The classification model is constructed based on one of a vector machine, a random forest or a deep learning network.

8. An ultrasonic carotid artery plaque type identification system, characterized in that: For implementing the method according to any one of claims 1 to 7, the system comprises: A carotid artery compression band is used to apply compression to the carotid artery and obtain mechanical data of the carotid artery before and after the compression; Ultrasound probe to obtain ultrasound images of the neck before and after compression of the carotid artery A signal processing module, used for preprocessing the neck ultrasound image; An image analysis module is used to reconstruct an image based on the neck ultrasound image, perform probability statistics on the area suspected of plaque in the reconstructed image, and identify the location and morphology of the plaque; Mechanical analysis module, used to analyze the mechanical response of the carotid artery during compression based on the carotid artery mechanical data; The soft and hard plaque judgment module is used to input the position, morphology and mechanical response of the identified plaque into the soft and hard plaque judgment model, and output the soft and hard type identification result of the plaque.

9. The ultrasonic carotid artery plaque type identification system according to claim 8, characterized in that: The system also includes an interactive module, including a user interactive interface, for displaying ultrasound images, plaque hardness and softness type judgment results and health advice, and providing a data export function.

10. A storage medium having a program stored thereon, characterized in that: When the program is executed, the method according to any one of claims 1 to 7 is implemented.

Images