Classification of skin lesions by fluorescence diagnosis and independent component analysis

H. G. Stockmeier, W. Bäumler, R. M. Szeimies, F. J. Theis, E. W. Lang, C. G. Puntonet

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

We develop an approach to automatically classify images of malignant and benign skin lesions obtained by Photodynamic Diagnosis. Our method does not use plain fluorescence intensity levels but relies on discriminative intensity patterns. Therefore a set of characteristic filter vectors is created for each class by independent component analysis. The results of the filtering process are fed into a supervised neural classifier. The classification results are promising. But further experiments with an increased data set taken under standardized image recording conditions seem necessary to yield still better classification rates.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Biomedical Engineering
EditorsB. Tilg
Pages201-204
Number of pages4
StatePublished - 2004
Externally publishedYes
EventProceedings of the IASTED International Conference on Biomedical Engineering - Innsbruck, Austria
Duration: 16 Feb 200418 Feb 2004

Publication series

NameProceedings of the IASTED International Conference on Biomedical Engineering

Conference

ConferenceProceedings of the IASTED International Conference on Biomedical Engineering
Country/TerritoryAustria
CityInnsbruck
Period16/02/0418/02/04

Keywords

  • Fluorescence diagnosis
  • Independent component analysis
  • Neural networks
  • Skin lesions

Fingerprint

Dive into the research topics of 'Classification of skin lesions by fluorescence diagnosis and independent component analysis'. Together they form a unique fingerprint.

Cite this