Application of generalized dynamic neural networks to biomedical data

Lutz Leistritz; Miroslaw Galicki; Eberhard Kochs; Ernst Bernhard Zwick; Clemens Fitzek; Jürgen R Reichenbach; Herbert Witte

doi:10.1109/TBME.2006.881766

Application of generalized dynamic neural networks to biomedical data

IEEE Trans Biomed Eng. 2006 Nov;53(11):2289-99. doi: 10.1109/TBME.2006.881766.

Authors

Lutz Leistritz¹, Miroslaw Galicki, Eberhard Kochs, Ernst Bernhard Zwick, Clemens Fitzek, Jürgen R Reichenbach, Herbert Witte

Affiliation

¹ Institute of Medical Statistics, Computer Sciences, and Documentation, Friedrich Schiller University Jena, Jena 07740, Germany. i6lelu@imsid.uni-jena.de

PMID: 17073335
DOI: 10.1109/TBME.2006.881766

Abstract

This paper reviews the application of continuous recurrent neural networks with time-varying weights to pattern recognition tasks in medicine. A general learning algorithm based on Pontryagin's maximum principle is recapitulated, and possibilities of improving the generalization capabilities of these networks are given. The effectiveness of the methods is demonstrated by three different real-world examples taken from the fields of anesthesiology, orthopedics, and radiology.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Biomedical Engineering / methods*
Databases, Factual
Diagnosis, Computer-Assisted / methods*
Information Storage and Retrieval / methods
Neural Networks, Computer*
Pattern Recognition, Automated / methods*
Signal Processing, Computer-Assisted*