How mengjindong/regionaldeepatrophy works
RDA uses longitudinal MRI to learn registration-based measures of Alzheimer’s disease progression and attention maps in the medial temporal lobe. The documented workflow starts with scan-pair training data, feeds paired scans through an attention/registration model, and trains against registration and progression-related objectives; testing evaluates warped segmentations with Dice overlap. The graph includes the core model, image preparation, and model persistence layers. Some connections are documented only in the README; unsampled testing and training details are not inferred beyond those statements.
Main entry points: networks.py Attention registration · train.py RDA training · test_attention.py Model testing · generators.py Scan-pair generators
Components 11
MRI data
- Scan-pair generators
vxm_model/generators.py - Image preparation
vxm_model/py/utils.py - CPU augmentation
vxm_model/py/data_aug_cpu.py
Model and transforms
- Attention registration
vxm_model/torch/networks.py - Spatial transforms
vxm_model/torch/layers.py - Registration losses
vxm_model/torch/losses.py
Training and evaluation
- RDA training
vxm_runs/torch/train.py - Model testing
vxm_runs/torch/test_attention.py
Model support
- Model persistence
vxm_model/torch/modelio.py
Other components
- Researcher
- Longitudinal MRI
Connections 11
- Researcher → RDA training: starts training
README.md - Longitudinal MRI → Scan-pair generators: provides scans
- RDA training → Scan-pair generators: uses scan pairs
README.md - Scan-pair generators → Image preparation: loads volumes
- Image preparation → CPU augmentation: uses augmentation
vxm_model/py/utils.py - RDA training → Attention registration: runs model
vxm_runs/torch/train.py - Attention registration → Spatial transforms: warps scans
vxm_model/torch/networks.py - Attention registration → Model persistence: inherits persistence
vxm_model/torch/networks.py - Researcher → Model testing: starts testing
README.md - Model testing → Model persistence: loads model
- Model testing → Longitudinal MRI: evaluates scans