Überatlas: Fast and robust registration for multi-atlas segmentation
Journal article, 2016

Multi-atlas segmentation has become a frequently used tool for medical image segmentation due to its outstanding performance. A computational bottleneck is that all atlas images need to be registered to a new target image. In this paper, we propose an intermediate representation of the whole atlas set – an überatlas – that can be used to speed up the registration process. The representation consists of feature points that are similar and detected consistently throughout the atlas set. A novel feature-based registration method is presented which uses the überatlas to simultaneously and robustly find correspondences and affine transformations to all atlas images. The method is evaluated on 20 CT images of the heart and 30 MR images of the brain with corresponding ground truth. Our approach succeeds in producing better and more robust segmentation results compared to three baseline methods, two intensity-based and one feature-based, and significantly reduces the running times.

Feature-based registration

Brain segmentation

Multi-atlas segmentation

Pericardium segmentation

Author

Jennifer Alvén

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Alexander Norlén

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Olof Enqvist

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Fredrik Kahl

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Pattern Recognition Letters

0167-8655 (ISSN)

Vol. 80 249-255

Areas of Advance

Information and Communication Technology

Life Science Engineering (2010-2018)

Subject Categories

Computer and Information Science

Computer Vision and Robotics (Autonomous Systems)

Medical Image Processing

DOI

10.1016/j.patrec.2016.05.001

More information

Latest update

7/23/2018