http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
R. Kanchana,R. Menaka 대한의용생체공학회 2020 Biomedical Engineering Letters (BMEL) Vol.10 No.3
Ischemic stroke is the dominant disorder for mortality and morbidity. For immediate diagnosis and treatment plan of ischemicstroke, computed tomography (CT) images are used. This paper proposes a histogram bin based novel algorithm to segmentthe ischemic stroke lesion using CT and optimal feature group selection to classify normal and abnormal regions. Stepsfollowed are pre-processing, segmentation, extracting texture features, feature ranking, feature grouping, classifi cation andoptimal feature group (FG) selection. The fi rst order features, gray level run length matrix features, gray level co-occurrencematrix features and Hu’s moment features are extracted. Classifi cation is done using logistic regression (LR), support vectormachine classifi er (SVMC), random forest classifi er (RFC) and neural network classifi er (NNC). This proposed approacheff ectively detects ischemic stroke lesion with a classifi cation accuracy of 88.77%, 97.86%, 99.79% and 99.79% obtained bythe LR, SVMC, RFC and NNC when FG12 is opted, which is validated by fourfold cross validation.