Tissue classification of a plaque is important for a diagnosis of the acute coronary syndromes. The conventional method however can not perform good classification, because the characteristics of some types of tissues have similar features with others. In this paper, we propose a novel feature extraction and classification method for intravascular ultrasound (IVUS) signal by using an adaptive subspace self-organizing map (ASSOM). In the proposed method, a tissue is classified by considering the statistical information of feature vectors acquired by ASSOM. The validity and the effectiveness of the proposed method are verified by applying it to the tissue classification problem of the real IVUS data.
