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...
Những tác giả chính: | Dinsdale, NK, Jenkinson, M, Namburete, AIL |
---|---|
Định dạng: | Journal article |
Ngôn ngữ: | English |
Được phát hành: |
Elsevier
2022
|
Những quyển sách tương tự
-
Unlearning scanner bias for MRI harmonisation in medical image segmentation
Bằng: Dinsdale, NK, et al.
Được phát hành: (2020) -
Anatomically plausible segmentations: explicitly preserving topology through prior deformations
Bằng: Wyburd, MK, et al.
Được phát hành: (2024) -
TEDS-Net: enforcing diffeomorphisms in spatial transformers to guarantee topology preservation in segmentations
Bằng: Wyburd, MK, et al.
Được phát hành: (2021) -
Unlearning scanner bias for MRI harmonisation
Bằng: Dinsdale, NK, et al.
Được phát hành: (2020) -
SFHarmony: source free domain adaptation for distributed neuroimaging analysis
Bằng: Dinsdale, NK, et al.
Được phát hành: (2024)