Multi-class classification algorithm for optical diagnosis of oral cancer

Majumder, S. K. ; Gupta, A. ; Gupta, S. ; Ghosh, N. ; Gupta, P. K. (2006) Multi-class classification algorithm for optical diagnosis of oral cancer Journal of Photochemistry and Photobiology B: Biology, 85 (2). pp. 109-117. ISSN 1011-1344

Full text not available from this repository.

Official URL: http://linkinghub.elsevier.com/retrieve/pii/S10111...

Related URL: http://dx.doi.org/10.1016/j.jphotobiol.2006.05.004

Abstract

We report development of a direct multi-class spectroscopic diagnostic algorithm for discrimination of high-grade cancerous tissue sites from low-grade as well as precancerous and normal squamous tissue sites of human oral cavity. The algorithm was developed making use of the recently formulated theory of total principal component regression (TPCR). The in vivo autofluorescence spectral data acquired from patients screened for neoplasm of oral cavity at the Government Cancer Hospital, Indore, was used to train and validate the algorithm. The diagnostic algorithm based on TPCR was found to provide satisfactory performance in classifying the tissue sites in four different classes - high-grade squamous cell carcinoma, low-grade squamous cell carcinoma, leukoplakia, and normal squamous tissue. The classification accuracy for these four classes was observed to be ~94%, 100%, 100% and 91% for the training data set (based on leave-one-out cross-validation), and was ~90%, 90%, 85% and 88%, respectively for the corresponding classes for the independent validation data set.

Item Type:Article
Source:Copyright of this article belongs to European Society for Photobiology.
Keywords:Autofluorescence Spectroscopy; Multi-class Classification; Diagnostic Algorithm; Leukoplakia; Oral Cancer; Total Principal Component Regression (TPCR); Squamous Cell Carcinoma (SCC)
ID Code:22250
Deposited On:23 Nov 2010 08:33
Last Modified:02 Jun 2011 06:44

Repository Staff Only: item control page