Whole Heart Segmentation
The Whole-heart segmentation (WHS) tool is a fully automated whole heart segmentation tool for 3D MR images or 3D CTA. The algorithm behind uses a multi-atlas propagation and fusion technique as described in Zuluaga et al. (FIMH 2013).
How to access it
It can be used via NiftyWeb, a web service tool that provides an entry point to our cutting edge algorithms:
WHS online tool
How to cite
We would appreciate it if the following references would be included in any published work that uses this resource:
MA. Zuluaga, MJ. Cardoso, M. Modat, S. Ourselin. Multi-atlas Propagation Whole Heart Segmentation from MRI and CTA Using a Local Normalised Correlation Coefficient Criterion. Functional Imaging and Modeling of the Heart, vol 7945, Lecture Notes in Computer Science, 174-181
http://niftyweb.cs.ucl.ac.uk/
F. Prados, MJ. Cardoso, N. Burgos, CAM. Wheeler-Kingshott, S. Ourselin. NiftyWeb: web based platform for image processing on the cloud. International Society for Magnetic Resonance in Medicine (ISMRM) 24th Scientific Meeting and Exhibition - Singapore 2016
Performance
The WHS tool has been benchmarked multiple times, showing state of the art perfomance. Further information can be found in the following publications:
- Right ventricle segmentation Challenge [PetitJean et al, MedIA 2015]
- Multi-modal left atrium segmentation [Tobon-Gomez et al, IEEE TMI 2015]
- Multi-modal whole heart segmentation [Zhuang et al, MedIA 2019]
