30P-C-10 ニューラルガスを用いた階層型k近隣法による冠動脈組織性状の判別速度および精度の向上(医療システム,一般講演)

概要

論文の詳細を見る
In this paper, we propose a method to advance the speed and accuracy for tissue classification of Intravascular Ultrasound (IVUS) data using Hierarchical k-Nearest Neighbor (HkNN). In this method, the neural gas is used to decide several representative vectors from the training vectors in the HkNN. The speed of calculation for tissue classification by HkNN is thus advanced. Moreover; the reliability and accuracy of the classification results are improved. They are examined by the experiments using the true IVUS data.
2011-10-29