Prostate MR image segmentation using 3D active appearance models

This paper presents a method for automatic segmentation of the prostate from transversal T2-weighted images based on 3D Active Appearance Models (AAM). The algorithm consist of two stages. Firstly, Shape Context based non-rigid surface registration of the manual segmented images is used to obtain the point correspondence between the given training cases. Subsequently, an AAM is used to segment the prostate on 50 training cases. The method is evaluated using a 5-fold cross validation over 5 repetitions. The mean Dice similarity coefficient and 95% Hausdorff distance are 0.78 and 7.32 mm respectively.

[1]  Jocelyne Troccaz,et al.  Atlas-based prostate segmentation using an hybrid registration , 2008, International Journal of Computer Assisted Radiology and Surgery.

[2]  Nico Karssemeijer,et al.  Segmentation of the Pectoral Muscle in Breast MRI Using Atlas-Based Approaches , 2012, MICCAI.

[3]  Cornelis H. Slump,et al.  MRI based knee cartilage assessment , 2012, Medical Imaging.

[4]  Olivier Colot,et al.  Combining a deformable model and a probabilistic framework for an automatic 3D segmentation of prostate on MRI , 2009, International Journal of Computer Assisted Radiology and Surgery.

[5]  Robert Marti,et al.  Atlas Based Segmentation of the prostate in MR images , 2009 .

[6]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[7]  Sébastien Ourselin,et al.  Automatic atlas-based segmentation of the prostate : A MICCAI 2009 Prostate Segmentation Challenge entry , 2009 .

[8]  Stefan Klein,et al.  Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information. , 2008, Medical physics.

[9]  Fabrice Mériaudeau,et al.  A hybrid framework of multiple active appearance models and global registration for 3D prostate segmentation in MRI , 2012, Medical Imaging.

[10]  Fabrice Mériaudeau,et al.  Prostate Segmentation with Texture Enhanced Active Appearance Model , 2010, 2010 Sixth International Conference on Signal-Image Technology and Internet Based Systems.

[11]  Anant Madabhushi,et al.  Integrating an adaptive region-based appearance model with a landmark-free statistical shape model: application to prostate MRI segmentation , 2011, Medical Imaging.

[12]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.