A vulnerable plaque identification and detection method, device and system for cardiovascular imaging

By performing grayscale analysis and determining the global segmentation threshold in cardiovascular images, combined with connected area segmentation and correlation quantification, the segmentation threshold is adjusted to solve the problem of poor identification and segmentation of vulnerable plaques in the existing technology, and achieve a better High detection accuracy.

CN118918136BActive Publication Date: 2025-01-21TIANJIN CHEST HOSPITAL
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411406051.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-10-10
Publication Date
2025-01-21
Estimated Expiration
2044-10-10

AI Technical Summary

Technical Problem

When identifying vulnerable plaques in cardiovascular images, the segmentation threshold is inaccurate due to the small difference in grayscale values, which affects the image segmentation effect.

Method used

Through grayscale analysis and determination of the global segmentation threshold, an iterative initial segmentation threshold is selected, and through connected area segmentation and quantification of the correlation between the long sides of both sides of the area's circumscribed rectangle and the blood vessel wall, the segmentation threshold is adjusted to improve the image of vulnerable plaques. Split effect.

Benefits of technology

It improves the image segmentation effect of vulnerable plaques in cardiovascular images and enhances the accuracy and reliability of detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118918136B_ABST
    Figure CN118918136B_ABST
Patent Text Reader

Abstract

The embodiment of the present application provides a vulnerable plaque identification and detection method, device and system for cardiovascular images, the method comprising acquiring a target cardiovascular image; performing grayscale analysis on the image, selecting an iterative initial segmentation threshold in a high grayscale region corresponding to a determined global segmentation threshold; performing connected region segmentation based on the initial segmentation threshold, determining the possibility of vulnerable plaques in each connected region by quantifying the correlation between the long sides of the circumscribed rectangle of the region and the vascular wall; comprehensively determining the segmentation threshold for the next iteration based on various vulnerable plaque possibilities; in two adjacent iterations, determining the performance of vulnerable plaques in two adjacent iteration regions based on the difference in vulnerable plaque probability before and after the iteration and the difference in segmentation thresholds; in the corresponding iteration, when it is determined that the required performance is greater than a preset threshold, outputting the segmentation result of the current iteration. The method can adaptively adjust the stop threshold of iterative threshold segmentation, thereby improving the image segmentation effect.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Easily-damaged plaque detection method and related equipment

    CN115511797A

  • Pavement crack detection system based on emulsified high-viscosity asphalt

    CN116934748A