A hybrid EfficientNet-R2-ASPP-dual-attention U-Net with Tversky loss reduces missed acute infarcts on DWI relative to common baselines on a 167-patient in-house dataset.
Tackling the class imbalance problem of deep learning-based head and neck organ segmentation,
1 Pith paper cite this work, alongside 24 external citations. Polarity classification is still indexing.
1
Pith paper citing it
24
external citations · OpenAlex
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EPRA U-Net: An Efficient Pyramid Residual Attention Framework for Accurate Infarct Segmentation in Diffusion-Weighted MRI
A hybrid EfficientNet-R2-ASPP-dual-attention U-Net with Tversky loss reduces missed acute infarcts on DWI relative to common baselines on a 167-patient in-house dataset.