Automatic segmentation of brain MRI in high-dimensional local and non-local feature space based on sparse representation

详细信息    查看全文

• 作者：Mohammad Mahdi Khalilzadeh^a ; ^{mmkhalilzadeh@gmail.com} ; Emad Fatemizadeh^b ; Hamid Behnam^c
• 关键词：Magnetic resonance image ; Image segmentation ; Sparse representation ; Local and non-local reconstruction error
• 刊名：Magnetic Resonance Imaging
• 出版年：2013
• 出版时间：June, 2013
• 年：2013
• 卷：31
• 期：5
• 页码：733-741
• 全文大小：1140 K

文摘

Automatic extraction of the varying regions of magnetic resonance images is required as a prior step in a diagnostic intelligent system. The sparsest representation and high-dimensional feature are provided based on learned dictionary. The classification is done by employing the technique that computes the reconstruction error locally and non-locally of each pixel. The acquired results from the real and simulated images are superior to the best MRI segmentation method with regard to the stability advantages. In addition, it is segmented exactly through a formula taken from the distance and sparse factors. Also, it is done automatically taking sparse factor in unsupervised clustering methods whose results have been improved.