Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

BrainWorld: A Structural-Prior-Conditioned Generative Model for Whole-Brain 4D fMRI Dynamics

About

Whole-brain 4D fMRI generation is valuable for modeling functional brain dynamics, yet existing fMRI foundation models mainly target representation learning and downstream prediction rather than conditional predictive generation. We introduce BrainWorld, a structural-prior-conditioned generative model for whole-brain 4D fMRI dynamics. BrainWorld uses sMRI as subject-level anatomical context to guide future fMRI generation, integrating structural information into the denoising process rather than treating it as a parallel modality. Evaluated on 22 datasets spanning diverse cohorts and brain states, BrainWorld generates stable 4D fMRI trajectories up to 400 frames, improves downstream performance through generated-example augmentation, and learns transferable multimodal representations that outperform baselines. Together, these results establish BrainWorld as a condition-aware generative framework for long-horizon brain dynamics modeling and multimodal representation learning.

Junfeng Xia, Wenhao Ye, Junxiang Zhang, Xuanye Pan, Mo Wang, Quanying Liu• 2026

Related benchmarks

TaskDatasetResultRank
Age regressionSALD
Mean Squared Error (MSE)0.107
23
Gender ClassificationABCD
Accuracy80.75
22
Disease DiagnosisADNI MCI
Accuracy76.27
19
fMRI predictionHCP Movie (External)
MSE0.437
15
Age regressionABIDE
MSE0.062
12
Brain Age PredictionNKI
MSE0.083
12
Gender ClassificationBHRC
Accuracy79.94
12
Education ClassificationNKI
Accuracy87.67
11
fMRI frame predictionSALD 40-frame External (test)
MSE0.186
10
fMRI predictionHCP LR1 (Internal)
MSE0.183
10
Showing 10 of 18 rows

Other info

Follow for update