Shape-aware multi-atlas segmentation
Paper i proceeding, 2017

Despite of having no explicit shape model, multi-atlas approaches to image segmentation have proved to be a top-performer for several diverse datasets and imaging modalities. In this paper, we show how one can directly incorporate shape regularization into the multi-atlas framework. Unlike traditional methods, our proposed approach does not rely on label fusion on the voxel level. Instead, each registered atlas is viewed as an estimate of the position of a shape model. We evaluate and compare our method on two public benchmarks: (i) the VISCERAL Grand Challenge on multi-organ segmentation of whole-body CT images and (ii) the Hammers brain atlas of MR images for segmenting the hippocampus and the amygdala. For this wide spectrum of both easy and hard segmentation tasks, our experimental quantitative results are on par or better than state-of-the-art. More importantly, we obtain qualitatively better segmentation boundaries, for instance, preserving fine structures.

Författare

Jennifer Alvén

Chalmers, Signaler och system, Signalbehandling och medicinsk teknik, Digitala bildsystem och bildanalys

Fredrik Kahl

Chalmers, Signaler och system, Signalbehandling och medicinsk teknik, Digitala bildsystem och bildanalys

Johan Fredriksson

Lunds universitet

Viktor Larsson

Lunds universitet

Jennifer Alvén

Lunds universitet

Proceedings - 23rd International Conference on Pattern Recognition, ICPR 2016, Cancun, Mexico, 4-8 December 2016

1051-4651 (ISSN)

1101-1106

Ämneskategorier

Datorseende och robotik (autonoma system)

DOI

10.1109/ICPR.2016.7899783

ISBN

9781509048472

Mer information

Senast uppdaterat

2018-03-02