How matteo-dunnhofer/mrpyrnet works
MRPyrNet adapts knee-MRI diagnosis pipelines for ACL and meniscal tears. In the MRNet variant, scans are loaded by view-specific datasets, trained and evaluated by per-view trainers, then per-view predictions are combined by logistic regression. The ELNet variant trains individual task/view models without the documented three-view ensemble. Both model implementations use pyramidal detail pooling; the MRNet model also uses an AlexNet backbone. The graph includes README-documented workflows where orchestration scripts are not shown; unsampled implementation details are not inferred.
Main entry points: MRNet+MRPyrNet/train_mrpyrnet_mrnet.py View training · ELNet+MRPyrNet/train_mrpyrnet_mrnet.py Task training · mrnetdataset.py MRNet dataset · mrpyrnet.py MRNet MRPyrNet
Components 13
MRI data
- MRNet dataset
MRNet+MRPyrNet/mrnetdataset.py - ELNet dataset
ELNet+MRPyrNet/mrnetdataset.py
MRNet pipeline
- View training
MRNet+MRPyrNet/train_mrpyrnet_mrnet.py - MRNet MRPyrNet
MRNet+MRPyrNet/mrpyrnet.py - Prediction ensemble
MRNet+MRPyrNet/train_logistic_regression.py
ELNet pipeline
- Task training
ELNet+MRPyrNet/train_mrpyrnet_mrnet.py - ELNet MRPyrNet
ELNet+MRPyrNet/mrpyrnet.py
Network components
- AlexNet backbone
modules/alexnet.py - Detail pooling
modules/pdp.py
Shared support
- MRI utilities
modules/utils.py
Other components
- Researcher
- MRNet scans
- Diagnosis metrics
Connections 17
- Researcher → View training: starts experiment
README.md - Researcher → Task training: starts experiment
README.md - MRNet scans → MRNet dataset: provides scans
README.md - MRNet scans → ELNet dataset: provides scans
README.md - View training → MRNet dataset: loads splits
MRNet+MRPyrNet/train_mrpyrnet_mrnet.py - View training → MRNet MRPyrNet: trains model
MRNet+MRPyrNet/train_mrpyrnet_mrnet.py - MRNet dataset → MRI utilities: augments scans
MRNet+MRPyrNet/mrnetdataset.py - MRNet MRPyrNet → AlexNet backbone: extracts features
MRNet+MRPyrNet/mrpyrnet.py - MRNet MRPyrNet → Detail pooling: pools details
MRNet+MRPyrNet/mrpyrnet.py - View training → Prediction ensemble: supplies view models
README.md - Prediction ensemble → MRNet dataset: loads evaluation data
MRNet+MRPyrNet/train_logistic_regression.py - Prediction ensemble → Diagnosis metrics: writes metrics
MRNet+MRPyrNet/train_logistic_regression.py - Task training → ELNet dataset: loads splits
ELNet+MRPyrNet/train_mrpyrnet_mrnet.py - Task training → ELNet MRPyrNet: trains model
ELNet+MRPyrNet/train_mrpyrnet_mrnet.py - ELNet dataset → MRI utilities: augments scans
ELNet+MRPyrNet/mrnetdataset.py - ELNet MRPyrNet → Detail pooling: pools details
ELNet+MRPyrNet/mrpyrnet.py - Task training → Diagnosis metrics: records metrics
ELNet+MRPyrNet/train_mrpyrnet_mrnet.py