Abstract

We investigated a novel method combining principal component analysis (PCA) and supervised learning technique, support vector machine (SVM), for classifying carcinoma lesion from normal tissue with light-induced autofluorescence. The autofluorescence spectral signals were collected in vivo from 85 nasopharyngeal carcinoma lesions and 131 normal tissue sites from 59 subjects during routine nasal endoscopy. With the combined PCA and SVM classifying algorithm, the achieved overall accuracy is over 97%, companied with 95% sensitivity and 99% specificity for discriminating carcinoma from normal tissue. In comparison with the previously developed algorithms based on PCA method, this new method outperforms threshold- and probability-based PCA algorithms in all instances. The experimental results indicate great promise for autofluorescence spectroscopy based detection of small carcinoma lesion in the nasopharynx and other tissues.

© 2003 SPIE

PDF Article
More Like This
Classification of autofluorescence spectra using the algorithm based on support vector machine

W. M. Lin, X. Yuan, P. C. Shi, J. N. Qu, P. W. Yuen, J. Sham, and W. I. Wei
CTuU6 Conference on Lasers and Electro-Optics (CLEO) 2003

Comparison of human colorectal normal tissue with cancerous tissue autofluorescence image by optical sectioning with a confocal laser-scanning microscope

Sheng Fu, Teck Chee Chia, Leong Chuan Kwek, Cheong Hoong Diong, Choong Leong Tang, Francis Seow Choen, and S.M. Krishnan
5139_199 European Conference on Biomedical Optics (ECBO) 2003

Application of laser induced autofluorescence spectra detection in human colorectal cancer screening

Sheng Fu, Teck Chee Chia, Leong Chuan Kwek, Cheong Hoong Diong, Choong Leong Tang, Francis Seow Choen, and S.M. Krishnan
5141_298 European Conference on Biomedical Optics (ECBO) 2003

References

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription