Full bibliography

Intrinsic fluorescence spectra of fresh normal and cancerous human breast tissues were measured using two selective excitation wavelengths including 290nm and 340nm. Dual-wavelength excitation may reveal more molecular information than single-wavelength excitation. In the meantime, it is significantly faster than the acquisition of excitation-emission (EEM) matrix. Unsupervised machine learning algorithms principal component analysis (PCA) and non-negative matrix factorization (NMF) were used to reduce the dimensionality of the spectral data. The relative concentrations of the basis spectra retrieved by PCA and NMF were considered features of the samples and used to distinguish normal and malignant tissues. The performances of classification using support vector machine (SVM) based on PCA and NMF features were compared. The classification using spectral data with dual-wavelength excitation was compared with single-wavelength excitation. Classification based on NMF-retrieved components from spectral data with dual-wavelength excitation yielded the best performance. © 2019 SPIE.

0 citations (Crossref) [2023-10-31] Journal Abbreviation: Progr. Biomed. Opt. Imaging Proc. SPIE