International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 31 - Issue 2 |
Published: October 2011 |
Authors: Imad Zyout, Phd, Ikhlas Abdel-Qader, Phd,Pe |
![]() |
Imad Zyout, Phd, Ikhlas Abdel-Qader, Phd,Pe . Article:Classification of Microcalcification Clusters via PSO-KNN Heuristic Parameter Selection and GLCM Features. International Journal of Computer Applications. 31, 2 (October 2011), 34-39. DOI=10.5120/3798-5235
@article{ 10.5120/3798-5235, author = { Imad Zyout,Phd,Ikhlas Abdel-Qader,Phd,Pe }, title = { Article:Classification of Microcalcification Clusters via PSO-KNN Heuristic Parameter Selection and GLCM Features }, journal = { International Journal of Computer Applications }, year = { 2011 }, volume = { 31 }, number = { 2 }, pages = { 34-39 }, doi = { 10.5120/3798-5235 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2011 %A Imad Zyout %A Phd %A Ikhlas Abdel-Qader %A Phd,Pe %T Article:Classification of Microcalcification Clusters via PSO-KNN Heuristic Parameter Selection and GLCM Features%T %J International Journal of Computer Applications %V 31 %N 2 %P 34-39 %R 10.5120/3798-5235 %I Foundation of Computer Science (FCS), NY, USA
Texture-based computer-aided diagnosis (CADx) of microcalcification clusters is more robust than the state-of-art shape-based CADx because the performance of shape-based approach heavily depends on the effectiveness of microcalcification (MC) segmentation. This paper presents a texture-based CADx that consists of two stages. The first one characterizes MC clusters using texture features from gray-level co-occurrence matrix (GLCM). In the second stage, an embedded feature selection based on particle swarm optimization and a k-nearest neighbor (KNN) classifier, called PSO-KNN, is applied to simultaneously determine the most discriminative GLCM features and to find the best k value for a KNN classifier. Testing the proposed CADx using 25 MC clusters from mini-MIAS dataset produced classification accuracy of 88% that obtained using 2 GLCM features.