Prior-based Coregistration and Cosegmentation

Mahsa Shakeri (1) , Enzo Ferrante (2, 3, 4) , Stavros Tsogkas (2, 3, 4) , Sarah Lippe (5, 6) , Samuel Kadoury (1) , Iasonas Kokkinos (4, 2, 3) , Nikos Paragios (2, 3, 4)

1 EPM - École Polytechnique de Montréal
2 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
3 CVN - Centre de vision numérique
4 Université Paris-Saclay
5 UdeM - Université de Montréal
6 CHU Sainte Justine [Montréal]

We propose a modular and scalable framework for dense coregistration and cosegmentation with two key characteristics: first, we substitute ground truth data with the semantic map output of a classifier; second, we combine this output with population deformable registration to improve both alignment and segmentation. Our approach deforms all volumes towards consensus, taking into account image similarities and label consistency. Our pipeline can incorporate any classifier and similarity metric. Results on two datasets, containing annotations of challenging brain structures, demonstrate the potential of our method.

Mots clés: Coregistration; Cosegmentation; Discrete optimization; Priors

Domaines: Imagerie médicale; Vision par ordinateur et reconnaissance de formes [cs.CV]

Mahsa Shakeri, Enzo Ferrante, Stavros Tsogkas, Sarah Lippe, Samuel Kadoury, et al.. Prior-based Coregistration and Cosegmentation. MICCAI 2016 - 19th International Conference on Medical Image Computing and Computer Assisted Intervention, 2016, Athens, Greece. ⟨hal-01349189⟩