Document Detail

Automatic Atlas-based Three-label Cartilage Segmentation from MR Knee Images.
MedLine Citation:
PMID:  23685704     Owner:  NLM     Status:  Publisher    
This paper proposes a method to build a bone-cartilage atlas of the knee and to use it to automatically segment femoral and tibial cartilage from T1 weighted magnetic resonance (MR) images. Anisotropic spatial regularization is incorporated into a three-label segmentation framework to improve segmentation results for the thin cartilage layers. We jointly use the atlas information and the output of a probabilistic k nearest neighbor classifier within the segmentation method. The resulting cartilage segmentation method is fully automatic. Validation results on 18 knee MR images against manual expert segmentations from a dataset acquired for osteoarthritis research show good performance for the segmentation of femoral and tibial cartilage (mean Dice similarity coefficient of 78.2% and 82.6% respectively).
Liang Shan; Cecil Charles; Marc Niethammer
Related Documents :
17032914 - High-spatial-resolution multistation mr angiography with parallel imaging and blood poo...
11148714 - Magnetic resonance imaging of large vessel vasculitis.
18097274 - Cervical ct angiography comparing routine noncontrast and a late venous scan as masks f...
8641094 - Comparison of magnetic resonance angiography with conventional angiography in the detec...
24233004 - Imaging of amyloid deposition in human brain using positron emission tomography and [(1...
25323104 - [(99m)tc]cflflf for early diagnosis and therapeutic evaluation in a rat model of acute ...
Publication Detail:
Journal Detail:
Title:  Proceedings / sponsored by IEEE Computer Society Technical Committee on Pattern Analysis and Machine Intelligence. Workshop on Mathematical Methods in Biomedical Image Analysis     Volume:  -     ISSN:  -     ISO Abbreviation:  Proc Workshop Math Methods Biomed Image Analysis     Publication Date:  2012  
Date Detail:
Created Date:  2013-5-20     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101525825     Medline TA:  Proc Workshop Math Methods Biomed Image Analysis     Country:  -    
Other Details:
Languages:  ENG     Pagination:  241-246     Citation Subset:  -    
Department of Computer Science, UNC Chapel Hill,
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Grant Support
R21 AR059890/AR/NIAMS NIH HHS; R21 AR059890-01A1/AR/NIAMS NIH HHS; R21 AR059890-02/AR/NIAMS NIH HHS

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Direct Imaging of ER Calcium with Targeted-Esterase Induced Dye Loading (TED).
Next Document:  HMGB1 release by human liver L02 and HepG2 cells induced by lipopolysaccharide.