Real-Time 3D Image Segmentation by User-Constrained Template Deformation

Benoît Mory (1) , Oudom Somphone (1) , Raphaël Prevost (1, 2) , Roberto Ardon (1)

1 Medisys - MedisysResearch Lab
2 CEREMADE - CEntre de REcherches en MAthématiques de la DEcision

We describe an algorithm for 3D interactive image segmenta- tion by non-rigid implicit template deformation, with two main original features. First, our formulation incorporates user input as inside/outside labeled points to drive the deformation and improve both robustness and accuracy. This yields inequality constraints, solved using an Augmented Lagrangian approach. Secondly, a fast implementation of non-rigid template-to-image registration enables interactions with a real-time visual feedback. We validated this generic technique on 21 Contrast-Enhanced Ultrasound images of kidneys and obtained accurate segmentation results (Dice> 0:93) in less than 3 clicks in average. Copyright Springer-Verlag Berlin Heidelberg 2012. The original publication is available at www.springerlink.com: http://link.springer.com/chapter/10.1007%2F978-3-642-33415-3_69.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]; Imagerie médicale

Benoît Mory, Oudom Somphone, Raphaël Prevost, Roberto Ardon. Real-Time 3D Image Segmentation by User-Constrained Template Deformation. The 15th International Conference on Medical Image Computing and Computer-Assisted Intervention - MICCAI 2012, Oct 2012, Nice, France. pp.561-568, ⟨10.1007/978-3-642-33415-3_69⟩. ⟨hal-00779423⟩