A Tissue Classification Method of IVOCT Images Using Rectangle Region Cropped along The Circumferential Direction Based on Deep Learning

摘要

Coronary artery disease (CAD) as a common disease is now indeed affecting the quality of daily life of patients.Qualification analysis of the causing reasons for this kind of disease needs more vessel inner tissue (healthy ornot healthy) information in detail. Recent years, an intravascular OCT technology is starting implemented tothe patients for a appropriate treatment. Lesion tissue analysis of thousands of IVOCT image data per patient istime-consuming and lower efficiency especially on manual analysing. Traditional machine learning methods arealways applied to investigate the feature extracted from the image data with some special feature engineeringtechnologies, but for deeper abstract features, it's still difficult to draw out. Currently, the utility of deep learningmethod to image target detection and classification tasks has won a great success and it's generally common touse the deep learning method attack many computer version issues. In this paper, we propose a method basedon the Convolutional Neural Network (CNN) to model a VGG-Net-like for category classification of vessel lesiontissues. We preprocess the IVOCT image with catheter and guide-wire removal methods and obtain the lumenboundary. Analyzing the intensity of vessel tissues with light attenuation, we crop rectangle regions with fixedsize along the circumferential direction to gain a number of patches as the input samples of CNN. Three kindsof input type, LBP-based single channel, RGB channels and merging-channel containing LBP and RGB, are fedinto the model we built to discuss the prediction results.