Affiliations:
College of Computer Science and Technology, Harbin Engineering University, Harbin, Heilongjiang, China
Correspondence:
[*]
Corresponding author. Haiwei Pan, College of Computer Science and Technology, Harbin Engineering University,
21Building, NO. 145 nantong street, ZIP code 150001, Harbin, Heilongjiang, China. Tel./Fax: +86 451 82519406; E-mail: [email protected].
Abstract: The high incidence of brain tumor has increased significantly in recent years. It is becoming more and more concernful to discover knowledge through mining medical brain image to aid doctors’ diagnosis. Clustering medical images for Intelligent Decision Support is an important part in the field of medical image mining because there are several technical aspects which make this problem challenging. In this paper, we propose a medical brain image clustering method to find similar pathology images that can assist doctors to analyze the specific disease, discover its potential cause and make more accurate treatment. Firstly, this method represents medical brain image dataset as a weighted, undirected and complete graph. Secondly, this graph is sparsified so as to describe the similarity of medical images very well. Last but not the least, a graph entropy based clustering method for this sparsified graph is proposed to cluster these medical images. The experimental results show that this method can cluster medical images efficiently and run well in time complexity. The clustering results can better describe the similarity of medical images.
Keywords: Medical image, graph entropy, sparsification, clustering
