Fuzzy preprocessing of gold standards as applied to a neural network classifier of magnetic resonance spectra

Author

Pizzi, Nicolino

Author_Institution

Dept. of Biodiagnostics, Nat. Res. Council of Canada, Winnipeg, Man., Canada

fYear

1997

fDate

22-23 May 1997

Firstpage

150

Lastpage

152

Abstract

Culling diagnostic information from biomedical spectra is often exasperated by an imperfect or imprecise gold standard. A fuzzy set theoretic preprocessing method is described that reduces the classification error rate by enhancing a gold standard through the incorporation of nonsubjective within-group centroid information. Magnetic resonance spectra of human brain neoplasms were used to determine the effectiveness of this strategy. A multi-layer perceptron classifier was used as the performance benchmark

Keywords

biomedical NMR; brain; diagnostic radiography; fuzzy set theory; image classification; medical image processing; multilayer perceptrons; spectral analysis; standards; biomedical spectra; classification error rate reduction; diagnostic information; fuzzy preprocessing; fuzzy set theoretic preprocessing method; gold standards; human brain neoplasms; magnetic resonance spectra; multilayer perceptron classifier; neural network classifier; nonsubjective within-group centroid information; performance benchmark; Artificial neural networks; Biological neural networks; Extraterrestrial measurements; Fuzzy neural networks; Fuzzy sets; Gold; Magnetic resonance; Multilayer perceptrons; Neural networks; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

WESCANEX 97: Communications, Power and Computing. Conference Proceedings., IEEE

Conference_Location

Winnipeg, Man.

Print_ISBN

0-7803-4147-3

Type

conf

DOI

10.1109/WESCAN.1997.627129

Filename

627129