We are happy to announce that our paper “Linking dynamic connectivity states to cognitive decline and anatomical changes in Alzheimer’s disease” has been published on NeuroImage by Elsevier. If you’re curious about early network signatures of Alzheimer’s disease, this work introduces an unsupervised model that embeds Hidden Markov Model dynamics in a CNN to extract recurring dynamic functional connectivity states from resting-state fMRI across controls, MCI, and AD. The study shows that how long the brain “dwells” in each state changes systematically with disease severity—supporting a two-stage trajectory of network disruption and providing a potential tool for early diagnosis and longitudinal monitoring.