Share Email Print
cover

Proceedings Paper

Evaluation of algorithm methods for fluorescence spectra of cancerous and normal human tissues
Author(s): Yang Pu; Wubao Wang; Robert R. Alfano
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The paper focus on the various algorithms on to unravel the fluorescence spectra by unmixing methods to identify cancerous and normal human tissues from the measured fluorescence spectroscopy. The biochemical or morphologic changes that cause fluorescence spectra variations would appear earlier than the histological approach; therefore, fluorescence spectroscopy holds a great promise as clinical tool for diagnosing early stage of carcinomas and other deceases for in vivo use. The method can further identify tissue biomarkers by decomposing the spectral contributions of different fluorescent molecules of interest. In this work, we investigate the performance of blind source un-mixing methods (backward model) and spectral fitting approaches (forward model) in decomposing the contributions of key fluorescent molecules from the tissue mixture background when certain selected excitation wavelength is applied. Pairs of adenocarcinoma as well as normal tissues confirmed by pathologist were excited by selective wavelength of 340 nm. The emission spectra of resected fresh tissue were used to evaluate the relative changes of collagen, reduced nicotinamide adenine dinucleotide (NADH), and Flavin by various spectral un-mixing methods. Two categories of algorithms: forward methods and Blind Source Separation [such as Principal Component Analysis (PCA) and Independent Component Analysis (ICA), and Nonnegative Matrix Factorization (NMF)] will be introduced and evaluated. The purpose of the spectral analysis is to discard the redundant information which conceals the difference between these two types of tissues, but keep their diagnostically significance. The facts predicted by different methods were compared to the gold standard of histopathology. The results indicate that these key fluorophores within tissue, e.g. tryptophan, collagen, and NADH, and flavin, show differences of relative contents of fluorophores among different types of human cancer and normal tissues. The sensitivity, specificity, and receiver operating characteristic (ROC) are finally employed as the criteria to evaluate the efficacy of these methods in cancer detection. The underlying physical and biological basis for these optical approaches will be discussed with examples. This ex vivo preliminary trial demonstrates that these different criteria from different methods can distinguish carcinoma from normal tissues with good sensitivity and specificity while among them, we found that ICA appears to be the superior method in predication accuracy.

Paper Details

Date Published: 7 March 2016
PDF: 9 pages
Proc. SPIE 9703, Optical Biopsy XIV: Toward Real-Time Spectroscopic Imaging and Diagnosis, 97031M (7 March 2016); doi: 10.1117/12.2205628
Show Author Affiliations
Yang Pu, The City College of New York (United States)
Wubao Wang, The City College of New York (United States)
Robert R. Alfano, The City College of New York (United States)


Published in SPIE Proceedings Vol. 9703:
Optical Biopsy XIV: Toward Real-Time Spectroscopic Imaging and Diagnosis
Robert R. Alfano; Stavros G. Demos, Editor(s)

© SPIE. Terms of Use
Back to Top