Self-supervised multimodal neuroimaging yields predictive representations for a spectrum of Alzheimer's phenotypes. (arXiv:2209.02876v1 [cs.LG])

Recent neuroimaging studies that focus on predicting brain disorders via
modern machine learning approaches commonly include a single modality and rely
on supervised over-parameterized models.However, a single modality provides
only a limited view of the highly complex brain. Critically, supervised models
in clinical settings lack accurate diagnostic labels for training. Coarse
labels do not capture the long-tailed spectrum of brain disorder phenotypes,
which leads to a loss of generalizability of the model that makes them less
useful in diagnostic settings. …

alzheimer's arxiv multimodal neuroimaging predictive