TY - GEN
T1 - TEDS-Net: enforcing diffeomorphisms in spatial transformers to guarantee topology preservation in segmentations
AU - Wyburd, Madeleine K.
AU - Dinsdale, Nicola K.
AU - Namburete, Ana I.L.
AU - Jenkinson, Mark
N1 - Funding Information:
MW and ND is supported by the Engineering and Physical Sciences Research Council (EPSRC) and Medical Research Council (MRC) [grant number EP/L016052/1]. MJ is supported by the National Institute for Health Research (NIHR) Oxford Biomedical Research Centre (BRC), and this research was funded by the Wellcome Trust [215573/Z/19/Z]. The Wellcome Centre for Integrative Neuroimaging is supported by core funding from the Wellcome Trust [203139/Z/16/Z]. AN is grateful for support from the UK Royal Academy of Engineering under the Engineering for Development Research Fellowships scheme.
PY - 2021
Y1 - 2021
N2 - Accurate topology is key when performing meaningful anatomical segmentations, however, it is often overlooked in traditional deep learning methods. In this work we propose TEDS-Net: a novel segmentation method that guarantees accurate topology. Our method is built upon a continuous diffeomorphic framework, which enforces topology preservation. However, in practice, diffeomorphic fields are represented using a finite number of parameters and sampled using methods such as linear interpolation, violating the theoretical guarantees. We therefore introduce additional modifications to more strictly enforce it. Our network learns how to warp a binary prior, with the desired topological characteristics, to complete the segmentation task. We tested our method on myocardium segmentation from an open-source 2D heart dataset. TEDS-Net preserved topology in 100 % of the cases, compared to 90 % from the U-Net, without sacrificing on Hausdorff Distance or Dice performance. Code will be made available at: www.github.com/mwyburd/TEDS-Net.
AB - Accurate topology is key when performing meaningful anatomical segmentations, however, it is often overlooked in traditional deep learning methods. In this work we propose TEDS-Net: a novel segmentation method that guarantees accurate topology. Our method is built upon a continuous diffeomorphic framework, which enforces topology preservation. However, in practice, diffeomorphic fields are represented using a finite number of parameters and sampled using methods such as linear interpolation, violating the theoretical guarantees. We therefore introduce additional modifications to more strictly enforce it. Our network learns how to warp a binary prior, with the desired topological characteristics, to complete the segmentation task. We tested our method on myocardium segmentation from an open-source 2D heart dataset. TEDS-Net preserved topology in 100 % of the cases, compared to 90 % from the U-Net, without sacrificing on Hausdorff Distance or Dice performance. Code will be made available at: www.github.com/mwyburd/TEDS-Net.
KW - Diffeomorphic
KW - Segmentation
KW - Spatial transformers
KW - Topology
UR - https://www.scopus.com/pages/publications/85116435671
U2 - 10.1007/978-3-030-87193-2_24
DO - 10.1007/978-3-030-87193-2_24
M3 - Conference contribution
AN - SCOPUS:85116435671
SN - 9783030871925
T3 - Lecture Notes in Computer Science
SP - 250
EP - 260
BT - Medical Image Computing and Computer Assisted Intervention – MICCAI 2021 - 24th International Conference, Proceedings
A2 - de Bruijne, Marleen
A2 - de Bruijne, Marleen
A2 - Cattin, Philippe C.
A2 - Cotin, Stéphane
A2 - Padoy, Nicolas
A2 - Speidel, Stefanie
A2 - Zheng, Yefeng
A2 - Essert, Caroline
PB - Springer Science and Business Media Deutschland GmbH
T2 - 24th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2021
Y2 - 27 September 2021 through 1 October 2021
ER -