Statistical techniques for diagnosing CIN using fluorescence spectroscopy: SVD and CART

A quantitative measure of intraepithelial neoplasia which can be made in vivo without tissue removal would be clinically significant in chemoprevention studies. Our group is working to develop such a technique based on fluorescence spectroscopy. Using empirically based algorithms, we have demonstrated that fluorescence is discriminating normal cervix from low- and high-grade cervical dysplasias with similar performance to colposcopy in expert hands. These measurements can be made in vivo, in near real time, and results can be obtained without biopsy. This paper describes a new method using automated analysis of fluorescence emission spectra to classify cervical tissue into multiple diagnostic categories. First, data is reduced using the singular value decomposition (SVD), yielding a set of orthogonal basis vectors. Each patient's emission spectrum is then fit by linear least squares regression to the basis vectors, producing a set of coefficients for each patient. Based on these coefficient values, the classification and regression tree (CART) method predicts the patient's classification. These results suggest that laser-induced fluorescence can be used to automatically recognize and differentially diagnose cervical intraepithelial neoplasia (CIN) at colposcopy. This method of analysis is general in nature, and can analyze fluorescence spectra of suspected intraepithelial neoplasms from other organ sites. As a more complete understanding of the biochemical and morphologic basis of tissue spectroscopy is developed, it may also be possible to use fluorescence spectroscopy of the cervix as a surrogate endpoint biomarker in Phase I and II chemoprevention trials.