Automatic identification of vulnerable plaques in cardiovascular optical coherence tomography OCT images

Abstract

A method for automatically identifying vulnerable plaques in cardiovascular optical coherence tomography OCT images, comprising the following steps: a) collecting cardiovascular OCT images; b) performing standardized processing on cardiovascular OCT images; c) performing easy processing on the standardized processed images Lesion plaque recognition processing, d) using the stacked self-encoding method to construct a deep learning model for the sample set: e) classify and identify; f) use the bilinear interpolation method to convert the Cartesian coordinate system; g) convert the coordinate system The image is divided into quadrants; h) judging whether there are two or more connected regions in the same quadrant in the quadranted image. Combined with the characteristics of cardiovascular OCT images, the sample data set is reconstructed to overcome the problem of limited sample number. In addition, the learning model is often affected by the training set. The present invention randomly selects samples from the data set multiple times to train the learning model, and forms an integrated learning model through a voting strategy. A large number of experiments have proved that this technology can achieve high recognition accuracy.

Description

technical field [0001] The invention relates to the technical fields of image analysis and machine learning, in particular to a method for automatic identification of vulnerable plaques in cardiovascular optical coherence tomography OCT images. Background technique [0002] Cardiovascular disease is the main cause of morbidity and death. With the advancement of image analysis and machine learning technology, the diagnosis and treatment of cardiovascular disease have developed rapidly. Optical coherence tomography (Optical Coherence Tomography, OCT) is a new medical imaging technology, which has been widely used in clinic. This technology has also been applied in cardiovascular imaging. It can distinguish the structure of blood vessel walls, accurately display the characteristics of atherosclerotic plaques, and identify vulnerable plaques. It plays a very important role in the diagnosis, identification, treatment and evaluation of cardiovascular lesions. . [0003] Before i...

AI Technical Summary

Problems solved by technology

In the field of medical image analysis, the number of labeled samples is limited, which brings great challenges to the application of deep learning in medical image analysis.

[0005] At present, through investigation and research, it is found that there is no automatic recognition technology for vulnerable plaques in cardiovascular OCT images using artificial intelligence technology at home and abroad.

Images