Multilayer Joint Segmentation Using MRF and Graph Cuts

Abstract

The problem of jointly segmenting objects, according to a set of labels (of cardinality L), from a set of images (of cardinality K) to produce K individual segmentations plus one joint segmentation, can be cast as a Markov Random Field model. Coupling terms in the considered energy function enforce the consistency between the individual segmentations and the joint segmentation. However, neither optimality on the minimizer (at least for particular cases), nor the sensitivity of the parameters, nor the robustness of this approach against standard ones have been clearly discussed before. This paper focuses on the case where L > 1, K > 1 and the segmentation problem is handled using graph cuts. Noticeably, some properties of the considered energy function are demonstrated, such as global optimality when L = 2 and K > 1, the link

Thin Structures Segmentation Using Anisotropic Neighborhoods

“…in image reconstruction [20]) and Potts regularization (e.g. in image segmentation [14]). Thin structures are however ubiquitous in a number of applications (such as medical imaging or quality control) and detecting them as accurately as possible is therefore of great interest.…”

Semi-automatic segmentation of whole-body images in longitudinal studies

“…They provide excellent results and have linear complexity. However, despite accelerations (Li et al 2004, Lermé et al 2010, they still require too much resources in terms of memory for applications in 3D medical imaging (Lermé et al 2010). Letʼs notice that methods based on MRF have also been tackled using Belief Propagation (Wang and Cohen 2005).…”