CN-121981943-A - Coronary calcification stability prediction system fusing IVUS image and hemodynamic data

CN121981943ACN 121981943 ACN121981943 ACN 121981943ACN-121981943-A

Abstract

The invention relates to the technical field of medical monitoring, in particular to a coronary calcification stability prediction system fusing IVUS images and hemodynamic data, which comprises a memory and a processor, wherein the coronary calcification stability prediction method can be realized; the method comprises the steps of obtaining a corrected IVUS image by processing an IVUS image based on a gray level co-occurrence matrix, determining a second three-dimensional relationship between the corrected IVUS image and a person to be tested based on a first three-dimensional relationship and a two-dimensional relationship, establishing a coronary calcification stability prediction model based on the corrected IVUS image and blood flow dynamic data, and obtaining a coronary calcification stability trend graph according to the coronary calcification stability prediction model so as to judge the stability of coronary calcification of the person to be tested. Through the arrangement, accuracy of coronary calcification judgment of the person to be tested can be improved.

Inventors

CHEN YUEWU
XI XIANGWEN
ZENG MENGYA
SUN GUOWEI
WANG LONGTAO

Assignees

陈跃武

Dates

Publication Date: 20260505
Application Date: 20251211

Claims (10)

1. A coronary calcification stability prediction system that fuses an IVUS image with hemodynamic data, the system comprising: a memory storing program instructions; A processor, which when executing the program instructions stored on the memory, implements a method of coronary calcification stability prediction, the method comprising: acquiring IVUS images and blood flow dynamic data of a to-be-detected person, wherein the IVUS images and the to-be-detected person have a preset first three-dimensional relationship; processing the IVUS image based on a gray level co-occurrence matrix to obtain a corrected IVUS image, wherein the corrected IVUS image and the IVUS image have a preset two-dimensional relationship; Determining a second three-dimensional relationship of the modified IVUS image and the subject based on the first three-dimensional relationship and the two-dimensional relationship; and establishing a coronary calcification stability prediction model based on the corrected IVUS image and the blood flow dynamic data, and acquiring a coronary calcification stability trend graph according to the coronary calcification stability prediction model so as to judge the stability of the coronary calcification of the tested person.
2. The coronary calcification stability prediction system of claim 1, wherein the acquiring IVUS images of the subject and modifying the IVUS images comprises: acquiring first three-dimensional visual data and second three-dimensional visual data, wherein the first three-dimensional visual data and the second three-dimensional visual data are at least acquired for the to-be-detected person; Acquiring a point cloud model of the person to be tested based on the first three-dimensional visual data, and gridding the point cloud model to acquire the IVUS image; And acquiring a corrected IVUS image of the person to be tested based on the second three-dimensional visual data.
3. The coronary calcification stability prediction system of claim 2, wherein the second three-dimensional visual data comprises an IVUS image set and a modified IVUS image set, wherein images in the modified IVUS image set can form the IVUS image, and wherein the image sharpness in the modified IVUS image set is higher than the image sharpness in the IVUS image set; The coronary calcification stability prediction method further comprises the following steps: and determining the first three-dimensional relationship between the IVUS image and the person to be tested based on the third three-dimensional relationship and the matching relationship between the image in the IVUS image set and the image in the corrected IVUS image set.
4. The coronary calcification stability prediction system of claim 1, wherein the IVUS image includes a plurality of first IVUS images, the plurality of first IVUS images being segmented by at least the IVUS images; the gray level co-occurrence matrix-based processing the IVUS image to obtain a corrected IVUS image, comprising: And respectively processing a plurality of first IVUS images through the gray level co-occurrence matrix, and obtaining a plurality of corrected IVUS images, wherein each corrected IVUS image has the two-dimensional relationship with a corresponding first IVUS image.
5. The coronary calcification stability prediction system of claim 1, wherein the gray level co-occurrence matrix-based processing of the IVUS image to obtain a corrected IVUS image comprises: Processing the IVUS image based on the gray scale co-occurrence matrix to obtain a second coronary sclerosis image; The second coronary sclerosis image is segmented into a plurality of the corrected IVUS images.
6. The coronary calcification stability prediction system of claim 1, wherein the first three-dimensional relationship is calculated by one of orthogonal projection, perspective projection, affine projection, sphere projection, cylinder projection, and cube projection.
7. The coronary calcification stability prediction system of claim 1 or 6, wherein the IVUS image and the hemodynamic data are fused, the coronary calcification stability prediction method is characterized by further comprising the following steps: Acquiring a three-dimensional coordinate of the person to be tested and a first two-dimensional coordinate of the IVUS image; the first three-dimensional relationship is a three-dimensional projection relationship of the three-dimensional coordinates and the first two-dimensional coordinates.
8. The coronary calcification stability prediction system of claim 1, wherein the computing the predetermined two-dimensional relationship comprises: Acquiring first two-dimensional coordinates of the IVUS image; acquiring a magnification between the IVUS image and the corrected IVUS image; calculating a second two-dimensional coordinate of the modified IVUS image based on the first two-dimensional coordinate and the magnification; And calculating the preset two-dimensional relation based on the first two-dimensional coordinate and the second two-dimensional coordinate.
9. The system of claim 1, wherein the establishing a coronary calcification stability prediction model based on the modified IVUS image and the hemodynamic data comprises: Obtaining coronary artery stability factors and model fault factors of corresponding coronary artery calcified patients according to the coronary artery calcified stability prediction model; optimizing the coronary calcification stability prediction model according to the model fault factors to obtain a second coronary calcification stability prediction model.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program for execution by a processor for a coronary calcification stability prediction system fusing an IVUS image with hemodynamic data as in any of the preceding claims 1-9.

Description

Coronary calcification stability prediction system fusing IVUS image and hemodynamic data Technical Field The invention relates to the technical field of medical monitoring, in particular to a coronary calcification stability prediction system fusing IVUS images and hemodynamic data. Background Coronary calcification is a significant feature of the development of atherosclerosis, the stability of which is directly related to the risk of acute cardiovascular events. At present, clinical evaluation mainly depends on imaging means such as intravascular ultrasound (IVUS), but the traditional IVUS images have resolution limitations, so that the microscopic features of calcified plaques are difficult to accurately quantify. Meanwhile, the single morphological evaluation cannot comprehensively reflect the functional state of the calcified plaque under the blood flow impact, and the key influence of the hemodynamic factors on the plaque stability is ignored. This results in deviations in the prior art prediction of coronary calcification stability, making it difficult to achieve accurate risk stratification. In addition, the existing prediction model often simply superimposes form and function data, lacks an effective fusion mechanism and self-optimizing capability, has insufficient generalization in different patient sub-groups, and influences the accuracy and reliability of clinical decisions. Therefore, a prediction system capable of deeply fusing high-precision morphological information and functional blood flow data is needed to solve the existing problems. Disclosure of Invention According to the invention, the coronary calcification stability prediction model is established through the IVUS image and the blood flow force data, and the coronary calcification stability trend graph is obtained through the coronary calcification stability prediction model so as to judge the stability of the coronary calcification of the tested person, so that the accuracy of judging the coronary calcification of the tested person can be improved. The technical scheme provided by the invention is that the coronary calcification stability prediction system fusing IVUS images and hemodynamic data comprises a memory and a processor, wherein the memory stores program instructions, and the processor executes the program instructions stored in the memory to realize a coronary calcification stability prediction method, which comprises the following steps: acquiring IVUS images and blood flow dynamic data of a to-be-detected person, wherein the IVUS images and the to-be-detected person have a preset first three-dimensional relationship; processing the IVUS image based on the gray level co-occurrence matrix to obtain a corrected IVUS image, wherein the corrected IVUS image and the IVUS image have a preset two-dimensional relationship; determining a second three-dimensional relationship between the corrected IVUS image and the subject based on the first three-dimensional relationship and the two-dimensional relationship; and establishing a coronary calcification stability prediction model based on the corrected IVUS image and the blood flow dynamic data, and acquiring a coronary calcification stability trend graph according to the coronary calcification stability prediction model so as to judge the stability of the coronary calcification of the person to be tested. Preferably, acquiring an IVUS image of the subject and correcting the IVUS image includes: acquiring first three-dimensional visual data and second three-dimensional visual data, wherein the first three-dimensional visual data and the second three-dimensional visual data are at least acquired for a person to be detected; based on the first three-dimensional visual data, acquiring a point cloud model of a person to be tested, and gridding the point cloud model to acquire an IVUS image; Based on the second three-dimensional visual data, a corrected IVUS image of the subject is acquired. Preferably, the second three-dimensional visual data comprises an IVUS image set and a corrected IVUS image set, wherein the image in the corrected IVUS image set can form an IVUS image, and the image definition in the corrected IVUS image set is higher than that in the IVUS image set; the coronary calcification stability prediction method further comprises the following steps: and determining a first three-dimensional relationship between the IVUS image and the person to be tested based on the third three-dimensional relationship and a matching relationship between the image in the IVUS image set and the image in the corrected IVUS image set. Preferably, the IVUS image comprises a plurality of first IVUS images, which are segmented at least by the IVUS images; Processing the IVUS image based on the gray co-occurrence matrix to obtain a modified IVUS image, comprising: And respectively processing the first IVUS images through the gray level co-occurrence matrix, and obtaining a plurality of correct