Browse by author
Lookup NU author(s): Ephraim Nwoye,
Professor Satnam Dlay,
Dr Wai Lok Woo,
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
Computer assisted diagnosis of colorectal cancer has received attention in recent years. The development of an automated algorithmic approach, based on quantitative measurements, would be a valuable tool to the pathologist for fast verification of these colon cancer abnormalities for effective treatment. In this paper a method which automatically locates differences in colon cell images and classy the colon cells into normal and malignant cells is presented. This system is implemented by fuzzifying image feature descriptor fractals and incorporating clustering paradigm with neural network to classify images. The proposed system was evaluated using 116 cancers and 88 normal colon cells images and shown to be more efficient, simple to implement and yields better accuracy than conventional methods. (17 References).
Author(s): Nwoye E, Dlay SS, Woo WL, Marghani KA
Publication type: Article
Publication status: Published
Journal: WSEAS Transactions on Systems
Print publication date: 01/01/2003
ISSN (print): 1109-2777
Publisher: World Scientific and Engineering Academy and Society