PRA-PoE aligns representations across modality subsets via learnable prototypes and fuses Gaussian experts with uncertainty-weighted precision to improve Alzheimer's diagnosis under missing data.
In: International conference on medical image computing and computer-assisted intervention
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PRA-PoE: Robust Multimodal Alzheimer's Diagnosis with Arbitrary Missing Modalities
PRA-PoE aligns representations across modality subsets via learnable prototypes and fuses Gaussian experts with uncertainty-weighted precision to improve Alzheimer's diagnosis under missing data.