STAMP: Simultaneous Training and Model Pruning for low data regimes in medical image segmentation
Acquisition of high quality manual annotations is vital for the development of segmentation algorithms. However, to create them we require a substantial amount of expert time and knowledge. Large numbers of labels are required to train convolutional neural networks due to the vast number of paramete...
Prif Awduron: | Dinsdale, NK, Jenkinson, M, Namburete, AIL |
---|---|
Fformat: | Journal article |
Iaith: | English |
Cyhoeddwyd: |
Elsevier
2022
|
Eitemau Tebyg
-
Unlearning scanner bias for MRI harmonisation in medical image segmentation
gan: Dinsdale, NK, et al.
Cyhoeddwyd: (2020) -
Anatomically plausible segmentations: explicitly preserving topology through prior deformations
gan: Wyburd, MK, et al.
Cyhoeddwyd: (2024) -
TEDS-Net: enforcing diffeomorphisms in spatial transformers to guarantee topology preservation in segmentations
gan: Wyburd, MK, et al.
Cyhoeddwyd: (2021) -
Unlearning scanner bias for MRI harmonisation
gan: Dinsdale, NK, et al.
Cyhoeddwyd: (2020) -
SFHarmony: source free domain adaptation for distributed neuroimaging analysis
gan: Dinsdale, NK, et al.
Cyhoeddwyd: (2024)