TEDS-Net: enforcing diffeomorphisms in spatial transformers to guarantee topology preservation in segmentations
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 fra...
Main Authors: | Wyburd, MK, Jenkinson, M, Dinsdale, NK, Namburete, AIL |
---|---|
Format: | Conference item |
Sprog: | English |
Udgivet: |
Springer
2021
|
Lignende værker
-
Anatomically plausible segmentations: explicitly preserving topology through prior deformations
af: Wyburd, MK, et al.
Udgivet: (2024) -
Cortical plate segmentation using CNNs in 3D fetal ultrasound
af: Wyburd, MK, et al.
Udgivet: (2020) -
Unlearning scanner bias for MRI harmonisation in medical image segmentation
af: Dinsdale, NK, et al.
Udgivet: (2020) -
STAMP: Simultaneous Training and Model Pruning for low data regimes in medical image segmentation
af: Dinsdale, NK, et al.
Udgivet: (2022) -
Preserving known anatomical topology in medical image segmentation using deep learning
af: Wyburd, MK
Udgivet: (2022)