Title: Cluster-based classification using self-organising maps for medical image databases

Authors: L.A. Silva, E. Del-Moral-Hernandez, R.A. Moreno, S.S. Furuie

Addresses: Department of Electronic Systems Engineering, University of Sao Paulo, Av. Prof. Luciano Gualberto Trav.3 N.158. CEP:05508-900, Cidade Universitaria, Sao Paulo, SP, Brasil. ' Department of Electronic Systems Engineering, University of Sao Paulo, Av. Prof. Luciano Gualberto Trav.3 N.158. CEP:05508-900, Cidade Universitaria, Sao Paulo, SP, Brasil. ' Heart Institute (InCor), University of Sao Paulo Medical School, Av. Dr. Eneas de Carvalho Aguiar, 44, 2o. Andar (Informatica), CEP:05403000, Sao Paulo, SP, Brasil. ' School of Engineering, University of Sao Paulo, Av. Prof. Luciano Gualberto Trav.3 N.158. CEP:05508-900, Cidade Universitaria, Sao Paulo, SP, Brasil

Abstract: Images are a fundamental source of information in medicine. They can support doctors and students in diagnostic decisions besides providing research and didactic material. The images stored in a database and divided in categories are an important step for data mining and content-based image retrieval (CBIR). This work addresses a methodology which joins the use of discrete wavelet transforms to characterise images and self-organising maps (SOM) neural networks to cluster based classification of medical images. This data mining methodology can be used in categorisation and in computer-aided diagnostic decision.

Keywords: artificial neural networks; ANNs; self-organising maps; SOM; data mining; medical images; wavelet transforms; categorisation; computer-aided diagnostic decisions; decision making.

DOI: 10.1504/IJICA.2009.027993

International Journal of Innovative Computing and Applications, 2009 Vol.2 No.1, pp.13 - 22

Published online: 26 Aug 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article