Explainable Prostate AI

Files

• train_model.py

This script is used to train the base model for the classification of voxels into benign an malignant

• train_features.py

This script is used to train the feature classifier based on feature annotations of known lesions.

• inference.py
• lesion_classifier_inference.py
• feature_classifier_inference.py

These three scripts are used for inference, whereas lesionClassifier_inference.py and featureClassifier_inference.py are contain the methods which are called from inference.py

Citation

Please cite

Interactive Explainable Deep Learning Model Informs Prostate Cancer Diagnosis at MRI Charlie A Hamm, Georg L Baumgärtner, Felix Biessmann, Nick L Beetz, Alexander Hartenstein, Lynn J Savic, Konrad Froböse, Franziska Dräger, Simon Schallenberg, Madhuri Rudolph, Alexander DJ Baur, Bernd Hamm, Matthias Haas, Sebastian Hofbauer, Hannes Cash, Tobias Penzkofer Radiology 2023 May;307(4):e222276. doi: 10.1148/radiol.222276. Epub 2023 Apr 11.

https://pubmed.ncbi.nlm.nih.gov/37039688/

Rights

Please note that all files are for reproducibility purposes only and are copyright (C) 2023 Quantitative Imaging Lab, Charité Universitätsmedizin Berlin, all rights reserved.