Share Email Print
cover

Proceedings Paper

Human glioma tumor grading using visible resonance Raman spectroscopy and machine learning (Conference Presentation)
Author(s): Binlin Wu; Yan Zhou; Shengjia Zhang; Xinguang Yu; Gangge Cheng; Ke Zhu; Cheng-hui Liu; Robert R. Alfano

Paper Abstract

Various machine learning algorithms will be presented to analyze spectral data collected by visible resonance Raman (VRR) spectroscopy to identify the cancer grades of human brain glioma tumors. The features were either based on selected fingerprint Raman peaks of key biomolecules, or retrieved by principal component analysis and partial least squares and artificial neural network (ANN). The grading was performed using multi-class classification using support vector machines, discriminant analysis and ANN. The most relevant features were searched using nested cross validation. The study showed VRR combined with machine learning provides a rapid robust molecular diagnostic tool for identifying cancer grades.

Paper Details

Date Published: 9 March 2020
PDF
Proc. SPIE 11234, Optical Biopsy XVIII: Toward Real-Time Spectroscopic Imaging and Diagnosis, 112340U (9 March 2020); doi: 10.1117/12.2547054
Show Author Affiliations
Binlin Wu, Southern Connecticut State Univ. (United States)
Yan Zhou, The General Hospital of the Air Force, PLA (China)
Shengjia Zhang, Jiangsu Raman Medical Equipment Co., Ltd. (China)
Xinguang Yu, The General Hospital of the Air Force, PLA (China)
Gangge Cheng, The General Hospital of the Air Force, PLA (China)
Ke Zhu, Chinese Academy of Sciences (China)
Cheng-hui Liu, The City College of New York (United States)
Robert R. Alfano, The City College of New York (United States)


Published in SPIE Proceedings Vol. 11234:
Optical Biopsy XVIII: Toward Real-Time Spectroscopic Imaging and Diagnosis
Robert R. Alfano; Stavros G. Demos; Angela B. Seddon, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray