部分最小二乗回帰による冠動脈プラークの組織性状判別

抄録

Tissue characterization of coronary plaque has to be performed in high accuracy for determining the treatment policy of percutaneous coronary intervention (PCI). We propose an algorithm to discriminate plaque tissue by applying partial least square (PLS) regression to the average of the frequency feature value of the remarkable tissue and its neighborhood tissues. The effectiveness of the proposed method is confirmed by applying it to the real intravascular ultrasound (IVUS) data.