期刊
20TH CONFERENCE ON MEDICAL IMAGE UNDERSTANDING AND ANALYSIS (MIUA 2016)
卷 90, 期 -, 页码 68-73出版社
ELSEVIER SCIENCE BV
DOI: 10.1016/j.procs.2016.07.012
关键词
Liver segmentation; grey-wolf optimisation; fuzzy c-means; support vector machine
In this paper, we present a computer-aided diagnosis (CAD) system for abdominal Computed Tomography liver images that comprises four main phases: liver segmentation, lesion candidate segmentation, feature extraction from each candidate lesion, and liver disease classification. A hybrid approach based on fuzzy clustering and grey wolf optimisation is employed for automatic liver segmentation. Fast fuzzy c-means clustering is used for lesion candidates extraction, and a variety of features are extracted from each candidate. Finally, these features are used in a classification stage using a support vector machine. Experimental results confirm the efficacy of the proposed CAD system, which is shown to yield an overall accuracy of almost 96% in terms of healthy liver extraction and 97% for liver disease classification (C) 2016 The Authors. Published by Elsevier B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据