Classifications of Liver Diseases from Medical Digital Images

Authors:
Lequan Min;Yongan Ye;Shubiao Gao
Affiliations:
Applied Science School/Information Engineering School, University of Science and Technology Beijing, Beijing, P.R. China 100083;Beijing University of Chinese Medicine, Beijing, P.R. China 100700;Beijing University of Chinese Medicine, Beijing, P.R. China 100700
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
Year:
2008

Citing 1
Cited 0

A computer-aided diagnostic system to characterize CT focal liver lesions: design and optimization of a neural network classifier

IEEE Transactions on Information Technology in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Hepatitis B/C virus (HBV/HCV) infections are serious problems of world-wide, which cause over million die each year. Most of HBV/HCV patients need long term therapy. Side effects and virus mutations make difficult to determine the durations and endpoints of treatments. Medical images of livers provide evaluating tools for effectiveness of anti-virus treatments. This paper presents a liver hepatitis progression model. Each class Ciin the model consists of three characteristic qualities: gray-scale characteristic interval IG, i, non-homogenous degree Nh, iand entropy Entroi. This model aims to describe both digitally and visually a patient's liver damage. Examples are given to explain how to use the liver hepatitis progress model to classify people with normal livers, healthy HBV carriers, light chronic HBV patients and chronic cirrhosis HBV patients. The results show that our analysis results are in agreement with the clinic diagnoses and provide quantitative and visual interpretations.