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...
Κύριοι συγγραφείς: | Dinsdale, NK, Jenkinson, M, Namburete, AIL |
---|---|
Μορφή: | Journal article |
Γλώσσα: | English |
Έκδοση: |
Elsevier
2022
|
Παρόμοια τεκμήρια
-
Unlearning scanner bias for MRI harmonisation in medical image segmentation
ανά: Dinsdale, NK, κ.ά.
Έκδοση: (2020) -
Anatomically plausible segmentations: explicitly preserving topology through prior deformations
ανά: Wyburd, MK, κ.ά.
Έκδοση: (2024) -
TEDS-Net: enforcing diffeomorphisms in spatial transformers to guarantee topology preservation in segmentations
ανά: Wyburd, MK, κ.ά.
Έκδοση: (2021) -
Unlearning scanner bias for MRI harmonisation
ανά: Dinsdale, NK, κ.ά.
Έκδοση: (2020) -
SFHarmony: source free domain adaptation for distributed neuroimaging analysis
ανά: Dinsdale, NK, κ.ά.
Έκδοση: (2024)