We report the development of a probability-based multi-class diagnostic algorithm to simultaneously distinguish highgrade
dysplasia from low-grade dysplasia, squamous metaplasia as well as normal human cervical tissues using nearinfrared
Raman spectra acquired in-vivo from the cervix of patients at the Vanderbilt University Medical Center.
Extraction of diagnostic features from the Raman spectra uses the recently formulated theory of nonlinear Maximum
Representation and Discrimination Feature (MRDF), and classification into respective tissue categories is based on the
theory of Sparse Multinomial Logistic Regression (SMLR), a recent Bayesian machine-learning framework of statistical
pattern recognition. The algorithm based on MRDF and SMLR was found to provide very good diagnostic performance
with a predictive accuracy of ~90% based on leave-one-out cross validation in classifying the tissue Raman spectra into
the four different classes, using histology as the "gold standard". The inherently multi-class nature of the algorithm
facilitates a rapid and simultaneous classification of tissue spectra into various tissue categories without the need to train
and heuristically combine multiple binary classifiers. Further, the probabilistic framework of the algorithm makes it
possible to predict the posterior probability of class membership in discriminating the different tissue types.
Raman spectroscopy has been shown to have the potential for providing differential diagnosis in the cervix with high sensitivity and specificity in previous in vitro and in vivo studies. A clinical study was designed at Vanderbilt University Medical Center to further evaluate the potential of near IR Raman spectroscopy for in vivo detection of squamous intra-epithelial neoplasia, a pre-cursor to cervical cancer, in a clinical setting. In this pilot in vivo clinical study, using a portable system, Raman spectra are collected using clinically feasible integration times during colposcopic evaluation. Multiple Raman spectra were acquired form colposcopically normal and abnormal sites prior to excision of tissue from patients with known abnormalities of the cervix. Measured Raman spectra were processed for nosie and background fluorescence using novel signal processing techniques. The resulting spectra were correlated with the corresponding histological diagnosis to determine empirical differences in spectra between different diagnostic categories. Using histology as the gold standard, multivariate statistical techniques were also used to develop discrimination algorithms with the hopes of developing this technique into a real time, non-invasive diagnostic tool.
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.