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...
Príomhchruthaitheoirí: | Dinsdale, NK, Jenkinson, M, Namburete, AIL |
---|---|
Formáid: | Journal article |
Teanga: | English |
Foilsithe / Cruthaithe: |
Elsevier
2022
|
Míreanna comhchosúla
Míreanna comhchosúla
-
Unlearning scanner bias for MRI harmonisation in medical image segmentation
de réir: Dinsdale, NK, et al.
Foilsithe / Cruthaithe: (2020) -
Anatomically plausible segmentations: explicitly preserving topology through prior deformations
de réir: Wyburd, MK, et al.
Foilsithe / Cruthaithe: (2024) -
TEDS-Net: enforcing diffeomorphisms in spatial transformers to guarantee topology preservation in segmentations
de réir: Wyburd, MK, et al.
Foilsithe / Cruthaithe: (2021) -
Unlearning scanner bias for MRI harmonisation
de réir: Dinsdale, NK, et al.
Foilsithe / Cruthaithe: (2020) -
SFHarmony: source free domain adaptation for distributed neuroimaging analysis
de réir: Dinsdale, NK, et al.
Foilsithe / Cruthaithe: (2024)