Predictions don't get you recovered! Where are the protocols that PREVENT BRAIN ATROPHY? You're all fired for massive incompetence!
Lesion-informed connectome diffusion modelling for individualized prediction of post-stroke brain atrophy
Gaolang Gong
Beijing Normal University https://orcid.org/0000-0001-5788-022X
Jing Yang
Beijing Normal University
Yixin Gao
Beijing Normal University
Liyuan Yang
Tianjin Normal University
Yaya Jiang
Beijing International Studies University
Wan Bin
University Hospitals of Genève
Şeyma Bayrak
Max Planck Institute for Human Cognitive and Brain Sciences
Xinyu Liang
Fudan University
Sofie Valk
Max Planck Institute for Human Cognitive and Brain Sciences
Maurizio Corbetta
Padova Neuroscience Center (PNC), University of Padova
Posted Date: August 5th, 2026
DOI: https://doi.org/10.21203/rs.3.rs-9954362/v1
Abstract
Remote brain atrophy after stroke is clinically consequential but difficult to predict at the
individual-patient level. Here we developed a lesion-informed connectome diffusion modelling
framework to forecast distributed grey matter volume (GMV) atrophy after focal stroke. Using
longitudinal MRI data from two stroke cohorts spanning the hyperacute, subacute and chronic
stages, we first showed that post-stroke GMV atrophy was more strongly constrained by
structural than by functional connectivity. We then initialized network diffusion models with
each patient’s lesion map and found that the resulting simulations captured individualized
atrophy patterns at 3 and 12 months post-stroke, whereas model performance was weak within
the first week after stroke. The model-derived propagation stage was not a simple proxy for
chronological time, but varied with lesion topography, lesion size, structural-network topology
and the molecular context of lesioned regions. Finally, lesion-derived features enabled out-of
sample prediction of individualized atrophy patterns without requiring longitudinal imaging.
These findings establish a computational framework for forecasting remote structural
degeneration after stroke from early lesion information, with potential utility for patient
stratification and individualized monitoring.
No comments:
Post a Comment