An intelligent medical image understanding method using two-tier neural network ensembles
IEA/AIE'2005 Proceedings of the 18th international conference on Innovations in Applied Artificial Intelligence
Transductive cost-sensitive lung cancer image classification
Applied Intelligence
Hi-index | 0.00 |
This paper presents an intelligent medical chromatic image understanding system for lung cancer cell identification based on fuzzy knowledge representation and reasoning. Following image analysis and a low-level feature extraction process, a two-layer rule-based fuzzy knowledge model is proposed to represent the domain knowledge needed for image understanding task. Experimental results show that the system achieves not only a high rate of overall correct identification, but also a low rate of false negative identification, that is, a low rate of identifying cancer cases to be normal ones, which is important in reducing false diagnosis cases.