Publications

BibTex format

@article{Lee:2019:10.1109/TMI.2019.2905990,
author = {Lee, M and Petersen, K and Pawlowski, N and Glocker, B and Schaap, M},
doi = {10.1109/TMI.2019.2905990},
journal = {IEEE Transactions on Medical Imaging},
pages = {2596--2606},
title = {TeTrIS: template transformer networks for image segmentation with shape priors},
url = {http://dx.doi.org/10.1109/TMI.2019.2905990},
volume = {38},
year = {2019}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - In this paper we introduce and compare different approaches for incorporating shape prior information into neural network based image segmentation. Specifically, we introduce the concept of template transformer networks where a shape template is deformed to match the underlying structure of interest through an end-to-end trained spatial transformer network. This has the advantage of explicitly enforcing shape priors and is free of discretisation artefacts by providing a soft partial volume segmentation. We also introduce a simple yet effective way of incorporating priors in state-of-the-art pixel-wise binary classification methods such as fully convolutional networks and U-net. Here, the template shape is given as an additional input channel, incorporating this information significantly reduces false positives. We report results on synthetic data and sub-voxel segmentation of coronary lumen structures in cardiac computed tomography showing the benefit of incorporating priors in neural network based image segmentation.
AU  - Lee,M
AU  - Petersen,K
AU  - Pawlowski,N
AU  - Glocker,B
AU  - Schaap,M
DO  - 10.1109/TMI.2019.2905990
EP  - 2606
PY  - 2019///
SN  - 0278-0062
SP  - 2596
TI  - TeTrIS: template transformer networks for image segmentation with shape priors
T2  - IEEE Transactions on Medical Imaging
UR  - http://dx.doi.org/10.1109/TMI.2019.2905990
UR  - http://hdl.handle.net/10044/1/69113
VL  - 38
ER  -

Download

Dr Ben Glocker

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)