MAE with spectral-domain reconstruction loss outperforms other self-supervised methods for MRI disease detection when the signal involves high-frequency anatomical structures.
Neurology74(3), 201–209 (2010)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
CSV-ViT proposes ROI-preserving variable-sized cortical supervertices and a mask-aware ViT to classify AD-related statuses from T1 MRI, reporting higher performance than recent surface models.
The paper introduces a time-resolved neural encoder combining Whisper embeddings with recurrent temporal modeling and soft attention to predict ECoG responses, finding strongest alignment in intermediate layers and anatomically coherent phoneme organization in electrodes.
citing papers explorer
-
Masked and Predictive Self-Supervised Foundation Models for 3D Brain MRI
MAE with spectral-domain reconstruction loss outperforms other self-supervised methods for MRI disease detection when the signal involves high-frequency anatomical structures.
-
CSV-ViT: A Vision Transformer with the Variable-sized Cortical Supervertices for Detection of Alzheimer's Disease Pathologies
CSV-ViT proposes ROI-preserving variable-sized cortical supervertices and a mask-aware ViT to classify AD-related statuses from T1 MRI, reporting higher performance than recent surface models.