Neural network-based colonoscopic diagnosis using on-line learning and differential evolution

• Published in: Applied soft computing 2004-09, Vol.4 (4), p.369-379
• Main Authors: Magoulas, George D, Plagianakos, Vassilis P, Vrahatis, Michael N
• Format: Article
• Language: English
• ISSN: 1568-4946
• DOI: 10.1016/j.asoc.2004.01.005

In this paper, on-line training of neural networks is investigated in the context of computer-assisted colonoscopic diagnosis. A memory-based adaptation of the learning rate for the on-line back-propagation (BP) is proposed and used to seed an on-line evolution process that applies a differential evolution (DE) strategy to (re-) adapt the neural network to modified environmental conditions. Our approach looks at on-line training from the perspective of tracking the changing location of an approximate solution of a pattern-based, and thus, dynamically changing, error function. The proposed hybrid strategy is compared with other standard training methods that have traditionally been used for training neural networks off-line. Results in interpreting colonoscopy images and frames of video sequences are promising and suggest that networks trained with this strategy detect malignant regions of interest with accuracy.