Automatic atherosclerotic heart disease detection in intracoronary optical coherence tomography images

Intracoronary optical coherence tomography (OCT) is a new invasive imaging system which produces high-resolution images of coronary arteries. Preliminary data suggests that the atherosclerotic disease can be detected from the intracoronary OCT images. However, manual assessment of the intracoronary OCT images is time-consuming and subjective. In this work, we present an automatic atherosclerotic disease detection system on intracoronary OCT images. In the system, a preprocessing scheme is first applied to remove speckle noise and artifacts caused by catheter. Intensity, Histograms of Oriented Gradients (HOG), and Local Binary Patterns (LBP) are then extracted to represent the OCT image. Finally a linear SVM classifier is employed to detect the unhealthy subject. Four-fold cross-validation process is conducted to evaluate the proposed system; and a dataset with 200 images from healthy subjects and 200 images from unhealthy subjects is built to evaluate the system. The mean accuracy is 0.90 and standard deviation is 0.0427, which indicates that the proposed system is accurate and stable.