A new tool for automated border detection and characterization of atherosclerotic plaque Composition in IVUS Images

Current intravascular ultrasound (IVUS) image processing techniques do not allow adequate and effective identification of the coronary artery plaques. This can be improved by defining and using appropriate features for the different kinds of the plaques which are usually developed within the arteries. In this paper, “Run-length” feature extraction method based on the so called algorithm is presented and used for improving the automated characterization of the atherosclerosis plaques within the IVUS images. The proposed method algorithm is applied to 200 IVUS images obtained from five different patients. A structure of weighted multi-class SVM permits the classification of the extracted feature vectors into three tissue classes, namely fibrofatty,necrotic core and calcified tissues. Results show our approach with an overall accuracy of 72%. The proposed methods for border detection and plaque characterization in this study were implemented to obtain a standalone executable application.     «

Current intravascular ultrasound (IVUS) image processing techniques do not allow adequate and effective identification of the coronary artery plaques. This can be improved by defining and using appropriate features for the different kinds of the plaques which are usually developed within the arteries. In this paper, “Run-length” feature extraction method based on the so called algorithm is presented and used for improving the automated characterization of the atherosclerosis plaques within th...     »