作者: W.I. Wei , P.W. Yuen , P.C. Shi , J. Sham , X. Yuan
DOI:
关键词:
摘要: A novel classification method based on support vector machine (SVM) technique is investigated to discriminate the cancerous tissue from normal with light induced autofluorescence signals. The spectra were measured in vivo 85 nasopharyngeal carcinoma lesions and 131 sites 59 subjects during routine nasal endoscopy. It was found that SVM algorithms able achieve diagnostic accuracy 94% sensitivity over 96% specificity. In comparison previously developed principal component analysis, we algorithm produced better diagnosing tissue.