Rough-Fuzzy Clustering:An Application to Medical Imagery

摘要：

A novel application of rough-fuzzy clustering is presented for synthetic as well as CT scan images of the brain.It is observed that the algorithm generates good prototypes even in the presence of outliers.The rough-fuzzy clustering simultaneously handles overlap of clusters and uncertainty involved in class boundary,thereby yielding the best approximation of a given structure in unlabeled data.The number of clusters is automatically optimized in terms of various validity indices.A comparative study is made with related partitive algorithms.Experimental results demonstrate the diagnosis of the extent of brain infarction in CT scan images,and is validated by medical experts.

关键词： Rough-fuzzy clustering cluster validation image segmenta-tion CT scan imaging

作者: Sushmita Mitra Bishal Barman

作者单位: Center for Soft Computing Research Indian Statistical Institute,Kolkata-700 108,India Electrical Engineering Department S.V.National Institute of Technology,Surat-395 007,Gujarat,India

会议类型: 国际会议

会议名称: The Third International Conference on Rough Sets and Knowledge Tevhnology(RSKT 2008)(第三届粗糙集与知识技术国际会议)

会议地点: 成都

会议语种:英文

页码: 300-307

在线出版日期: 2008-05-17（万方平台首次上网日期，不代表论文的发表时间）