Attention-augmented U-Nets segment multi-etiology WMHs on public FLAIR datasets; morphological features from the masks classify vascular versus demyelinating origin at accuracy close to ground-truth masks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Attention-Based Segmentation of WMHs and Differentiation of Vascular vs. Demyelinating Lesions
Attention-augmented U-Nets segment multi-etiology WMHs on public FLAIR datasets; morphological features from the masks classify vascular versus demyelinating origin at accuracy close to ground-truth masks.