OCT cardiovascular plaque automatic identification and analysis method based on deep learning

Abstract

The invention provides an OCT cardiovascular plaque automatic identification and analysis method based on deep learning, which comprises the following steps of: processing a depth cross section: performing segmentation processing on the depth cross section of an OCT image to obtain a segmentation result A1; performing cross section processing: performing segmentation processing on the cross section of the OCT image to obtain a segmentation result A2; comprehensive section processing: synthesizing the depth section processing result A1 and the cross section processing result A2, and performing segmentation processing to obtain a segmentation result A; and result analysis: according to the segmentation result A, calculating a plaque attenuation index IPA to obtain a plaque category. The method is reasonable in design, integrates classification characteristics of different images and clinical characteristics of OCT, performs three-dimensional reconstruction and segmentation on the 3D OCT image, obtains a quantitative index IPA, and finally classifies plaques based on the IPA, and can effectively solve the problem of weak plaque identification capability in the prior art.

Description

technical field [0001] The present invention relates to the field of image analysis, in particular to an automatic recognition and analysis method of OCT cardiovascular plaque based on deep learning. Background technique [0002] Cardiovascular disease has developed into the number one killer of disease deaths among Chinese residents, and has caused immeasurable harm to Chinese national health and national economic development. Unstable lipid plaques are a major cause of coronary heart disease, the number one fatal cardiovascular disease. [0003] Due to its ultra-high imaging resolution (10-20μm), intravascular optical coherence tomography (intravascular optical coherencetomography, IV-OCT) technology has rapidly developed into an effective method for the diagnosis of coronary heart disease. IV-OCT images can clearly show different types of atherosclerotic plaques, known as "living tissue microscope". [0004] In terms of plaque segmentation, N. Gessert et al. pre-trained...

AI Technical Summary

Problems solved by technology

However, for the 3D image of OCT, the image produced by the interference of optical instruments, in which the plaque is usually relatively small, and it is a 3D image, the ability to identify different plaques is usually relatively weak, and there are certain defects.

Images