We report the results of a comparative evaluation of in vivo fluorescence and Raman spectroscopy for diagnosis of oral
neoplasia. The study carried out at Tata Memorial Hospital, Mumbai, involved 26 healthy volunteers and 138 patients
being screened for neoplasm of oral cavity. Spectral measurements were taken from multiple sites of abnormal as well as
apparently uninvolved contra-lateral regions of the oral cavity in each patient. The different tissue sites investigated
belonged to one of the four histopathology categories: 1) squamous cell carcinoma (SCC), 2) oral sub-mucous fibrosis
(OSMF), 3) leukoplakia (LP) and 4) normal squamous tissue. A probability based multivariate statistical algorithm
utilizing nonlinear Maximum Representation and Discrimination Feature for feature extraction and Sparse Multinomial
Logistic Regression for classification was developed for direct multi-class classification in a leave-one-patient-out cross
validation mode. The results reveal that the performance of Raman spectroscopy is considerably superior to that of
fluorescence in stratifying the oral tissues into respective histopathologic categories. The best classification accuracy was
observed to be 90%, 93%, 94%, and 89% for SCC, SMF, leukoplakia, and normal oral tissues, respectively, on the basis
of leave-one-patient-out cross-validation, with an overall accuracy of 91%. However, when a binary classification was
employed to distinguish spectra from all the SCC, SMF and leukoplakik tissue sites together from normal, fluorescence
and Raman spectroscopy were seen to have almost comparable performances with Raman yielding marginally better
classification accuracy of 98.5% as compared to 94% of fluorescence.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.