Automated Classification of Liver Disorders using Ultrasound Images

Authors:
Fayyaz Ul Minhas;Durre Sabih;Mutawarra Hussain
Affiliations:
Department of Computer Science, Colorado State University, Fort Collins, USA 80523;Multan Institute of Nuclear Medicine and Radiotherapy (MINAR), Multan, Pakistan;Department of Computer Science, Pakistan Institute of Engineering and Applied Sciences, Nilore, Pakistan
Venue:
Journal of Medical Systems
Year:
2012

Citing 5
Cited 0

Texture Classification by Wavelet Packet Signatures

IEEE Transactions on Pattern Analysis and Machine Intelligence
A tutorial on ν-support vector machines: Research Articles

Applied Stochastic Models in Business and Industry - Statistical Learning
Texture Analysis of Ultrasonic Liver Image Based on Wavelet Transform and Probabilistic Neural Network

BMEI '08 Proceedings of the 2008 International Conference on BioMedical Engineering and Informatics - Volume 02
Fatty Liver Characterization and Classification by Ultrasound

IbPRIA '09 Proceedings of the 4th Iberian Conference on Pattern Recognition and Image Analysis
Diffuse liver disease classification from ultrasound surface characterization, clinical and laboratorial data

IbPRIA'11 Proceedings of the 5th Iberian conference on Pattern recognition and image analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel approach for detection of Fatty liver disease (FLD) and Heterogeneous liver using textural analysis of liver ultrasound images. The proposed system is able to automatically assign a representative region of interest (ROI) in a liver ultrasound which is subsequently used for diagnosis. This ROI is analyzed using Wavelet Packet Transform (WPT) and a number of statistical features are obtained. A multi-class linear support vector machine (SVM) is then used for classification. The proposed system gives an overall accuracy of ~95% which clearly illustrates the efficacy of the system.