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...
主要な著者: | Dinsdale, NK, Jenkinson, M, Namburete, AIL |
---|---|
フォーマット: | Journal article |
言語: | English |
出版事項: |
Elsevier
2022
|
類似資料
-
Unlearning scanner bias for MRI harmonisation in medical image segmentation
著者:: Dinsdale, NK, 等
出版事項: (2020) -
Anatomically plausible segmentations: explicitly preserving topology through prior deformations
著者:: Wyburd, MK, 等
出版事項: (2024) -
TEDS-Net: enforcing diffeomorphisms in spatial transformers to guarantee topology preservation in segmentations
著者:: Wyburd, MK, 等
出版事項: (2021) -
Unlearning scanner bias for MRI harmonisation
著者:: Dinsdale, NK, 等
出版事項: (2020) -
SFHarmony: source free domain adaptation for distributed neuroimaging analysis
著者:: Dinsdale, NK, 等
出版事項: (2024)