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

Khalilzadeh, M. M ; Sharif University of Technology | 2013

875 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.mri.2012.11.010
  3. Publisher: 2013
  4. Abstract:
  5. 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
  6. Keywords:
  7. Image segmentation ; Local and non-local reconstruction error ; Magnetic resonance image ; Sparse representation ; Accuracy ; Analytical error ; Automation ; Cluster analysis ; Computer simulation ; Controlled study ; Human ; Image analysis ; Image reconstruction ; Imaging and display ; Nuclear magnetic resonance imaging ; Physical parameters ; Priority journal ; Algorithms ; Artificial Intelligence ; Brain ; Humans ; Image Enhancement ; Image Interpretation, Computer-Assisted ; Imaging, Three-Dimensional ; Magnetic Resonance Imaging ; Pattern Recognition, Automated ; Reproducibility of Results ; Sensitivity and Specificity
  8. Source: Magnetic Resonance Imaging ; Volume 31, Issue 5 , 2013 , Pages 733-741 ; 0730725X (ISSN)
  9. URL: http://www.mrijournal.com/action/doSearch?searchType=quick&searchText=Automatic+segmentation+of+brain+MRI+in+high-dimensional+local+and+non-local+feature+space+based+on+sparse+representation&occurrences=articleTitleAbstractKeywords&journalCode=mri&searchScope=fullSite