A single 3D MAE-pretrained xLSTM-UNet encoder transfers to infarct classification, meningioma segmentation, and brain-age estimation, taking second place on the FOMO 2025 Method Track.
Although task -specific supervised models can achieve strong performance, their development depends on labelled datasets that are costly to curate and often limited in size
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
BrainNext: A General-Purpose Self-Supervised Foundation Model for Brain MRI Analysis
A single 3D MAE-pretrained xLSTM-UNet encoder transfers to infarct classification, meningioma segmentation, and brain-age estimation, taking second place on the FOMO 2025 Method Track.