Automatic segmentation of human brain sulci

A Conditional Random Field Approach for Coupling Local Registration with Robust Tissue and Structure Segmentation

“…These models can be easily deduced from the conditional distribution p(t, s, θ|y) confirming that there is no need to define the complete joint model p(t, s, y, θ) and emphasizing the rational of using a CRF approach for segmentation purpose. Moreover, the model definition in (1) induces that the conditional models p(t|s, y, θ) and p(s|t, y, θ) are MRF with energy functions denoted by H(t|s, y, θ) and H(s|t, y, θ) obtained by omiting in expression (1) the terms that do not depend on t, resp. on s. The two-stage E-step (2) and (3) requires then to compute H…”

“…Recently growing interest has been on tackling this complexity by combining different approaches. As an illustration, Yang et al [1] propose to use a region based tissue classification approach followed by a watershed algorithm to label brain sulci while Yu et al [2] combine a regionbased bias field estimation and a level set method to segment the cortex. A step further the combinaison of methods is coupling, giving the possibility to introduce mutual interactions between components of a model.…”

Spectral Forests: Learning of Surface Data, Application to Cortical Parcellation

“…In particular, the accurate segmentation of cortical surfaces into major folds, or sulcal areas, is fundamental to many applications involving region-specific measurements. Two strategies exist for cortical parcellation and are either template based [1][2][3][4][5][6][7], via iterative deformations of a pre-labeled atlas, or subject based, via costly processing of sulcal data [8][9][10] or extracted sulcal lines [11][12][13]. Present methods often suffer from a heavy computational burden.…”

A New Hybrid Method for the Segmentation of the Brain MRIS

“…Yu et al [19] fused methods by set of level (implicit deformable models) with Bayesian techniques to segment the cortex. Yang and Kruggel [20] combine Bayesian approaches with Watershed algorithms to segment the cortical sulci.…”