|
|
|
|
|
June 2002, Volume 1, Number 2, Pages 130-138
|
|
|
|
Table of contents Previous Full text Next PDF
|
|
|
 |
| Original Article |
| Liver cancer detection system based on the analysis of digitized color images of tissue samples obtained using needle biopsy |
|
| Mohamed Sammouda1, Rachid Sammouda2, Noboru Niki1 and Kiyoshi Mukai3 |
|
1Department of Optical Science and Technology, Faculty of Engineering, University of Tokushima, Tokushima, Japan
2Department of Computer Science, University of Sharjah, UAE
3Department of Pathology, Tokyo Medical University, Tokyo, Japan
|
Correspondence to: Mohamed Sammouda, University of Tokushima, Faculty of Engineering, Department of Optical Science and Technology, minami-josanjima-cho 2-1, 770-8506, Tokushima, Japan. Tel: +81 88 656 9432; Fax: +81 88 656 9433 E-mail: mohamed@opt.tokushima-u.ac.jp or sammouda@hotmail.com |
|
| Keywords |
| liver cancer; segmentation; pathological color image; artificial neural networks; chromaticity features; labeling, diagnostic rules |
|
| Abstract |
| In this article, the authors propose a method for automatic diagnosis of liver cancer based on analysis of digitized color images of liver tissue obtained by needle biopsy. The approach is a combination of an unsupervised segmentation algorithm, using a modified artificial Hopfield neural network (HNN), and an analysis algorithm based on image quantization. The segmentation algorithm is superior to HNN in the sense that it converges to a nearby global minimum rather than a local one in a prespecified time. Furthermore, as the segmentation of color images does not only depend on the segmentation algorithm but also on the color space representation, and in order to choose the best segmentation result, segmentation was performed with HNN and using components of the raw image with respect to each of the RGB, HLS, and HSV color spaces. Then, the segmented image was labeled based on chromaticity features and histogram analysis of the RGB color space components of the raw image. The image regions were then classified into normal and cancerous using diagnostic rules formulated based on those used by experienced pathologists in the clinic. The proposed method provides quantitative satisfactory results in diagnosing a liver pathological image set of 17 cases. Information Visualization (2002) 1, 130-138. doi:10.1057/palgrave.ivs.9500012 |
|
Table of contents Previous Full text Next PDF
|
|
|
|
