Weakly Supervised Group-Wise Model Learning Based on Discrete Optimization

In this paper we propose a method for the weakly supervised learning of sparse appearance models from medical image data based on Markov random fields (MRF). The models are learnt from a single annotated example and additional training samples without annotations. The approach formulates the model learning as solving a set of MRFs. Both the model training and the resulting model are able to cope with complex and repetitive structures. The weakly supervised model learning yields sparse MRF appearance models that perform equally well as those trained with manual annotations, thereby eliminating the need for tedious manual training supervision. Evaluation results are reported for hand radiographs and cardiac MRI slices.

[1]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[2]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Rachid Deriche,et al.  Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Yanxi Liu,et al.  Computer Vision for Biomedical Image Applications, First International Workshop, CVBIA 2005, Beijing, China, October 21, 2005, Proceedings , 2005, CVBIA.

[5]  Nassir Navab,et al.  Dense image registration through MRFs and efficient linear programming , 2008, Medical Image Anal..

[6]  Horst Bischof,et al.  Active Feature Models , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[7]  Timothy F. Cootes,et al.  3D Statistical Shape Models Using Direct Optimisation of Description Length , 2002, ECCV.

[8]  Nicholas Ayache,et al.  Medical Image Computing and Computer-Assisted Intervention - MICCAI 2007, 10th International Conference, Brisbane, Australia, October 29 - November 2, 2007, Proceedings, Part I , 2007, MICCAI.

[9]  Markus Vincze,et al.  Efficient Texture Representation Using Multi-scale Regions , 2007, ACCV.

[10]  Horst Bischof,et al.  Sparse MRF Appearance Models for Fast Anatomical Structure Localisation , 2007, BMVC.

[11]  W. Eric L. Grimson,et al.  Efficient Population Registration of 3D Data , 2005, CVBIA.

[12]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[13]  Timothy F. Cootes,et al.  Groupwise Construction of Appearance Models using Piece-wise Affine Deformations , 2005, BMVC.

[14]  Mads Nielsen,et al.  Computer Vision — ECCV 2002 , 2002, Lecture Notes in Computer Science.

[15]  Horst Bischof,et al.  Robust Autonomous Model Learning from 2D and 3D Data Sets , 2007, MICCAI.