DocumentCode :
2442228
Title :
Pyramidal neural networking for mammogram tumour pattern recognition
Author :
Xing, Guoxin ; Feltham, Richard
Author_Institution :
Wakefield Radiol. Ltd., Wellington, New Zealand
Volume :
6
fYear :
1994
fDate :
27 Jun- 2 Jul 1994
Firstpage :
4090
Abstract :
There has been much interest in developing neural networks to solve complicated information processing problems such as automatic diagnosis of x-ray mammograms. In New Zealand the authors are investigating a pyramidal neural network and adaptive contrast enhancement image processing technique for developing a knowledge-system for medical image interpretation. In this paper the authors present the pyramidal network architecture with experimental breast cancer tumour pattern mapping results. The pyramidal network configuration has overcome the problem of hidden layer size. To facilitate the learning the authors introduced a novel method of standard coding mechanism by using local overlapping and minimum value thresholding. The outcome of this unique mapping is promising in designing a useful expert system
Keywords :
diagnostic expert systems; diagnostic radiography; image enhancement; image recognition; medical expert systems; medical image processing; neural nets; New Zealand; adaptive contrast enhancement image processing technique; automatic diagnosis; expert system; knowledge-system; learning; local overlapping; mammogram tumour pattern recognition; medical image interpretation; minimum value thresholding; pyramidal neural networking; standard coding mechanism; Adaptive systems; Biomedical imaging; Breast cancer; Image coding; Image processing; Information processing; Medical diagnostic imaging; Neural networks; Tumors; X-ray imaging;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
Type :
conf
DOI :
10.1109/ICNN.1994.374869
Filename :
374869
Link To Document :
بازگشت