Optical Biopsy for Prostate Cancer Diagnosis Using Fluorescence Spectroscopy
Native fluorescence spectra are acquired from fresh normal and cancerous human prostate tissues. The fluorescence data are analyzed using an unsupervised machine learning algorithm such as non-negative matrix factorization. The nonnegative spectral components are retrieved and attributed to the native fluorophores such as collagen, reduced nicotinamide adenine dinucleotide (NADH), and flavin adenine dinucleotide (FAD) in tissue. The retrieved scores of the components are used to estimate the relative concentrations of the native fluorophores such as NADH and FAD and the redox ratio. A supervised machine learning algorithm such as support vector machine (SVM) is used to classify normal and cancerous tissue samples based on either the relative concentrations of NADH and FAD or the redox ratio alone. Various statistical measures such as sensitivity, specificity, and accuracy, along with the area under receiver operating characteristic (ROC) curve are used to show the classification performance. A cross validation method such as leave-one-out is used to further evaluate the predictive performance of the SVM classifier to avoid bias due to overfitting, and the accuracy was found to be 93.3%.