Unlearning scanner bias for MRI harmonisation
Combining datasets is vital for increased statistical power, especially for neurological conditions where limited data is available. However, variance due to differences in acquisition protocol and hardware limits our ability to combine datasets. We propose an iterative training scheme based on doma...
Main Authors: | Dinsdale, NK, Jenkinson, M, Namburete, AIL |
---|---|
Format: | Conference item |
Language: | English |
Published: |
Springer
2020
|
Similar Items
-
Unlearning scanner bias for MRI harmonisation in medical image segmentation
by: Dinsdale, NK, et al.
Published: (2020) -
Deep learning-based unlearning of dataset bias for MRI harmonisation and confound removal.
by: Dinsdale, NK, et al.
Published: (2020) -
FedHarmony: unlearning scanner bias with distributed data
by: Dinsdale, N, et al.
Published: (2022) -
STAMP: Simultaneous Training and Model Pruning for low data regimes in medical image segmentation
by: Dinsdale, NK, et al.
Published: (2022) -
SFHarmony: source free domain adaptation for distributed neuroimaging analysis
by: Dinsdale, NK, et al.
Published: (2024)