Share Email Print
cover

Proceedings Paper

Tumor diagnosis using the backpropagation neural network method
Author(s): Lixing Ma; Sydney Sukuta; Reinhard F. Bruch; Natalia I. Afanasyeva; Carl G. Looney
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

For characterization of skin cancer, an artificial neural network method has been developed to diagnose normal tissue, benign tumor and melanoma. The pattern recognition is based on a three-layer neural network fuzzy learning system. In this study, the input neuron data set is the Fourier transform IR spectrum obtained by a new fiberoptic evanescent wave Fourier transform IR spectroscopy method in the range of 1480 to 1850 cm-1. Ten input features are extracted from the absorbency values in this region. A single hidden layer of neural nodes with sigmoids activation functions clusters the feature space into small subclasses and the output nodes are separated in different nonconvex classes to permit nonlinear discrimination of disease states. The output is classified as three classes: normal tissue, benign tumor and melanoma. The results obtained from the neural network pattern recognition are shown to be consistent with traditional medical diagnosis. Input features have also been extracted from the absorbency spectra using chemical factor analysis. These abstract features or factors are also used in the classification.

Paper Details

Date Published: 24 April 1998
PDF: 11 pages
Proc. SPIE 3257, Infrared Spectroscopy: New Tool in Medicine, (24 April 1998); doi: 10.1117/12.306094
Show Author Affiliations
Lixing Ma, Univ. of Nevada/Reno (United States)
Sydney Sukuta, Univ. of Nevada/Reno (United States)
Reinhard F. Bruch, Univ. of Nevada/Reno (United States)
Natalia I. Afanasyeva, Univ. of Nevada/Reno (United States)
Carl G. Looney, Univ. of Nevada/Reno (United States)


Published in SPIE Proceedings Vol. 3257:
Infrared Spectroscopy: New Tool in Medicine
Henry H. Mantsch; Michael Jackson, Editor(s)

© SPIE. Terms of Use
Back to Top