Fig. 1
From: Effective workflow from multimodal MRI data to model-based prediction
A workflow for model-based prediction research. It can be divided into five steps. The first step is the acquisition of multi-modal MRI data (T1-weighted, diffusion-weighted, and resting-state functional MRI). The second step is preprocessing the acquired MRI data, which can be used for neuroimaging analysis. The third step is to calculate whole-brain tractography and apply a brain parcellation to reconstruct the whole-brain structural and functional connectomes. The fourth step involves whole-brain dynamical modeling including parameter optimization, where the optimal whole-brain model is identified and used to simulate and investigate the brain dynamics in silico. The final step is applying the simulated data for machine-learning analyses.
