Interactive Liver Tumor Segmentation Using Graph-cuts and Watershed

Jean Stawiaski (1) , Etienne Decencière (1) , François Bidault (2)

1 CMM - Centre de Morphologie Mathématique
2 IGR - Institut Gustave Roussy

We present in this paper an application of minimal surfaces and Markov random fields to the segmentation of liver tumors. The originality of the work consists in applying these models to the region adja-cency graph of a watershed transform. We detail the assumptions and the approximations introduced in these models by using a region graph instead of a pixel graph. This strategy leads to an interactive method used to delineate tumors in 3D CT images. We detail our strategy to achieve relevant segmentations of these structures and compare our results to hand made segmentations done by experienced radiologists. This paper summarizes our participation to the MICCAI 2008 3 workshop called: " 3D segmentation in the clinic : A Grand Challenge II " .

Domaines: Imagerie médicale; Traitement des images [eess.IV]; Imagerie; Cancer

Jean Stawiaski, Etienne Decencière, François Bidault. Interactive Liver Tumor Segmentation Using Graph-cuts and Watershed. 11th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2008), Sep 2008, New York, NY, United States. ⟨hal-01445751⟩