Stokes shift spectroscopy and machine learning for label-free human prostate cancer detection

Abstract

The Stokes shift spectra (S3) of human cancerous and normal prostate tissues were collected label free at a selected wavelength interval of 40 nm to investigate the efficacy of the approach based on three key molecules—tryptophan, collagen, and reduced nicotinamide adenine dinucleotide (NADH)—as cancer biomarkers. S3 combines both fluorescence and absorption spectra in one scan. The S3 spectra were analyzed using machine learning (ML) algorithms, including principal component analysis (PCA), nonnegative matrix factorization (NMF), and support vector machines (SVMs). The components retrieved from the S3 spectra were considered principal biomarkers. The differences in the weights of the components between the two types of tissues were found to be significant. Sensitivity, specificity, and accuracy were calculated to evaluate the performance of SVM classification. This research demonstrates that S3 spectroscopy is effective for detecting the changes in the relative concentrations of the endogenous fluorophores in tissues due to the development of cancer label free.