テンプレートマッチングを用いたラクナ梗塞検出のためのコンピュータ支援診断システムの改良

概要

論文の詳細を見る
The detection of lacunar infarcts is important because their presence indicates an increased risk of severe cerebral infarction. However, their accurate identification is often hard because of the difficulty in distinguishing between lacunar infarcts and Virchow-Robin spaces. The purpose of this study is to improve our CAD scheme by using template matching for reduction of false positives (FPs) . Our database comprised 1,143 T1- and 1,143 T2-weighted images obtained from 132 patients. The proposed method was evaluated by using 2 hold cross validation method. As a result, 17.1％ of FPs were eliminated more by adding the template matching to our previous CAD scheme. Conclusively, the sensitivity of the detection of lacunar infarcts was 96.8％ (90／93) with 0.59 FP per slice image. Our improved CAD scheme would be useful in assisting radiologists for identifying lacunar infarcts in MR images.