Primal/Dual Linear Programming and Statistical Atlases for Cartilage Segmentation

In this paper we propose a novel approach for automatic segmentation of cartilage using a statistical atlas and efficient primal/dual linear programming. To this end, a novel statistical atlas construction is considered from registered training examples. Segmentation is then solved through registration which aims at deforming the atlas such that the conditional posterior of the learned (atlas) density is maximized with respect to the image. Such a task is reformulated using a discrete set of deformations and segmentation becomes equivalent to finding the set of local deformations which optimally match the model to the image. We evaluate our method on 56 MRI data sets (28 used for the model and 28 used for evaluation) and obtain a fully automatic segmentation of patella cartilage volume with an overlap ratio of 0.84 with a sensitivity and specificity of 94.06% and 99.92%, respectively.

[1]  Nikos Komodakis,et al.  Fast, Approximately Optimal Solutions for Single and Dynamic MRFs , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  E. Yelin,et al.  Cost of musculoskeletal diseases: impact of work disability and functional decline. , 2003, The Journal of rheumatology. Supplement.

[3]  Ole Fogh Olsen,et al.  Automatic Segmentation of the Articular Cartilage in Knee MRI Using a Hierarchical Multi-class Classification Scheme , 2005, MICCAI.

[4]  Guido Gerig,et al.  Medical Image Computing and Computer-Assisted Intervention - MICCAI 2005, 8th International Conference, Palm Springs, CA, USA, October 26-29, 2005, Proceedings, Part II , 2005, MICCAI.

[5]  Stuart Crozier,et al.  Automatic segmentation of the bone and extraction of the bone–cartilage interface from magnetic resonance images of the knee , 2007, Physics in medicine and biology.

[6]  David Suter,et al.  Development of Semi-Automatic Segmentation Methods for Measuring Tibial Cartilage Volume , 2005, Digital Image Computing: Techniques and Applications (DICTA'05).

[7]  Guido Gerig,et al.  Valmet: A New Validation Tool for Assessing and Improving 3D Object Segmentation , 2001, MICCAI.

[8]  Wiro J. Niessen,et al.  Medical Image Computing and Computer-Assisted Intervention – MICCAI 2001 , 2001, Lecture Notes in Computer Science.

[9]  Scott T. Acton,et al.  Surface extraction and thickness measurement of the articular cartilage from MR images using directional gradient vector flow snakes , 2006, IEEE Transactions on Biomedical Engineering.

[10]  F. Eckstein,et al.  Magnetic resonance imaging (MRI) of articular cartilage in knee osteoarthritis (OA): morphological assessment. , 2006, Osteoarthritis and cartilage.

[11]  Nassir Navab,et al.  Inter and Intra-modal Deformable Registration: Continuous Deformations Meet Efficient Optimal Linear Programming , 2007, IPMI.

[12]  Alexander V. Tikhonov,et al.  Ill-Posed Problems in Natural Sciences , 1989 .

[13]  Claude Kauffmann,et al.  Computer-aided method for quantification of cartilage thickness and volume changes using MRI: validation study using a synthetic model , 2003, IEEE Transactions on Biomedical Engineering.

[14]  Haiying Liu,et al.  A Generic Framework for Non-rigid Registration Based on Non-uniform Multi-level Free-Form Deformations , 2001, MICCAI.

[15]  Ron Kikinis,et al.  Improved watershed transform for medical image segmentation using prior information , 2004, IEEE Transactions on Medical Imaging.

[16]  David Suter,et al.  A comparision of model-based methods for knee cartilage segmentation , 2007, VISAPP.

[17]  Nikos Paragios,et al.  Prior Knowledge, Level Set Representations & Visual Grouping , 2008, International Journal of Computer Vision.

[18]  Claus Christiansen,et al.  Semi-automatic knee cartilage segmentation , 2006, SPIE Medical Imaging.

[19]  Monica Barbu-McInnis,et al.  Unsupervised definition of the tibia-femoral joint regions of the human knee and its applications to cartilage analysis , 2006, SPIE Medical Imaging.