HU-based foreground masking, which trains masked image models only on subvolumes with mean intensity above 0.1, improves downstream 3D medical segmentation Dice by 0.3 to 2.9 points over random masking baselines.
The Lancet Digital Health6(11), e815–e826 (2024)
1 Pith paper cite this work, alongside 103 external citations. Polarity classification is still indexing.
1
Pith paper citing it
103
external citations · OpenAlex
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HU-based Foreground Masking for 3D Medical Masked Image Modeling
HU-based foreground masking, which trains masked image models only on subvolumes with mean intensity above 0.1, improves downstream 3D medical segmentation Dice by 0.3 to 2.9 points over random masking baselines.