Shape-aware multi-atlas segmentation
Paper in proceeding, 2016

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.

Author

Jennifer Alvén

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Lund University

Fredrik Kahl

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Lund University

Matilda Landgren

Lund University

Viktor Larsson

Lund University

Johannes Ulén

Lund University

Proceedings - International Conference on Pattern Recognition

1051-4651 (ISSN)

Vol. 0 1101-1106 7899783

23rd International Conference on Pattern Recognition, ICPR 2016
Cancun, Mexico,

Subject Categories

Computer Vision and Robotics (Autonomous Systems)

DOI

10.1109/ICPR.2016.7899783

More information

Latest update

5/19/2021