A Better Classifier Based on Rough Set and Neural Network for Medical Images
- 1 January 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 23759232,p. 853-857
Abstract
Detecting tumor in mammography is a difficult task because of complexity in the image. This brings the necessity of creating automatic tools to find whether a mammography present tumor or not. In this paper we integrate neural network with reduction of rough set theory which we call the rough neural network (RNN) to classify digital mammography. The experimental results show that the RNN performs better than purely using neural network in terms of time, and it can get 92.37% classifying accuracy which is higher than 81.25% using neural network onlyKeywords
This publication has 7 references indexed in Scilit:
- Feature extraction from mammographic images using fast marching methodsNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2002
- A novel self-optimizing approach for knowledge acquisitionIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2002
- Evaluation of texture methods for image analysis2001
- Data Mining via Discretization, Generalization and Rough Set Feature SelectionKnowledge and Information Systems, 1999
- Markov random field for tumor detection in digital mammographyIEEE Transactions on Medical Imaging, 1995
- MAMMOGRAM SCREENING USING MULTIRESOLUTION-BASED IMAGE SEGMENTATIONInternational Journal of Pattern Recognition and Artificial Intelligence, 1993
- Rough setsInternational Journal of Parallel Programming, 1982