A method and device for automatic detection of thin fibrous cap plaques based on cardiovascular OCT images

Abstract

The present invention relates to a method and device for automatic detection of thin fibrous cap plaques based on cardiovascular OCT images. The method includes: using N OCT images to establish an OCT image data set; Test atlas; use the OCT training atlas containing thin fiber cap plaque information to train the network to be trained to form a post-training network, which is used to detect and classify the OCT test atlas; use the post-training network to detect and classify the OCT test atlas Thin fibrous cap plaque detection and thin fibrous cap plaque classification are performed on the test atlas; thin fibrous cap plaques are prompted according to the classification results. The present invention uses the trained network to extract features from the image, realizes automatic detection and identification of whether there is a thin fibrous cap plaque on the OCT image, does not require manual participation, and is convenient for doctors to accurately analyze the OCT image, and the detection accuracy is relatively high. High, with better robustness and detection speed.

Description

Technical field[0001]The present invention relates to the technical field of medical devices, in particular to a method and device for automatically detecting thin fiber cap plaques based on cardiovascular OCT images.Background technique[0002]Vulnerable plaques refer to all plaques that easily lead to thrombosis or can quickly develop into disease. The envelope on the surface of vulnerable plaque is very thin, and the plaque contains a lot of lipids, so it is easy to rupture. For example, emotional stimulation, strenuous exercise, alcoholism, cold and other factors can cause the human body to increase blood pressure, blood flow violently impacts the plaque, or vasospasm. In these cases, the capsule of the vulnerable plaque will be damaged and ruptured.[0003]At present, thin fibrous cap plaque (TCFA) with inflammation infiltration is the most common type of vulnerable plaque. Acute coronary events caused by its secondary plaque rupture account for 60-70% of all coronary events.[0004]...

AI Technical Summary

Problems solved by technology

[0004] Although there are many methods for the detection of thin fibrous cap plaques, including coronary angiography, intravascular ultrasound, optical coherence tomography, etc., they all need to be based on manual identification of whether the image contains thin fibrous cap plaques, and the current clinical evaluation and analysis of cardiac Vascular thin fibrous cap plaques require doctors to spend a lot of time and energy to analyze and judge whether OCT images contain thin fibrous cap plaques; on the other hand, it cannot meet the needs of real-time clinical analysis and cannot establish a unified clinical standard

Images