A New Method of Medical Image Classification Using Neural Networks Committees

Biomedical Engineering: Proceedings of the 12th International Conference 2008
Maksims Alekseičevs, Aleksandrs Glazs

The motivation for our work is to develop an efficient method of classification for medical images, which will be able to distinguish healthy patient from diseases one, using neural networks committees. In this work the possibility of using different committee methods is analyzed. It is shown, that for successfully solving the given task, any reviewed committee method may be used, because their results have the same reliability of classification.

Atslēgas vārdi
Neural networks; Neural network ensemble; Plurality voting; Ensemble average; Weighted voting

Alekseičevs, M., Glazs, A. A New Method of Medical Image Classification Using Neural Networks Committees. No: Biomedical Engineering: Proceedings of the 12th International Conference, Lietuva, Kaunas, 23.-24. oktobris, 2008. Kaunas: Technologija, 2008, 229.-232.lpp. ISBN 978-9955-25-576-5.

Publikācijas valoda
English (en)