{"id":"W3165750456","doi":"10.1038/s42256-021-00337-8","title":"End-to-end privacy preserving deep learning on multi-institutional medical imaging","year":2021,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":470,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institute on Governance","funders":"Deutschen Konsortium für Translationale Krebsforschung; Technische Universität München; Deutsche Forschungsgemeinschaft; Imperial College London; UK Research and Innovation","keywords":"Computer science; USable; Inference; Convolutional neural network; Encryption; Deep learning; Artificial intelligence; Machine learning; Information privacy; End-to-end principle; Computer security; Data mining; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001930813,0.0008189033,0.001206966,0.0005060307,0.0007459053,0.001964247,0.002023875,0.001814149,0.002876519],"category_scores_gemma":[0.006023618,0.0005183773,0.0007134832,0.0006728231,0.001126827,0.003261143,0.004440668,0.002214398,0.001025511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001137552,"about_ca_system_score_gemma":0.001864574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002527019,"about_ca_topic_score_gemma":0.005543518,"domain_scores_codex":[0.9983159,0.0004901479,0.00007330393,0.0003406452,0.0004554221,0.0003245806],"domain_scores_gemma":[0.9977616,0.0008221757,0.000155285,0.0008344869,0.0002821449,0.000144215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001825894,0.0006716709,0.005734211,0.000214299,0.0002343252,0.0009487059,0.0003132747,0.4231524,0.01983042,0.04278925,0.01806499,0.4862206],"study_design_scores_gemma":[0.00001553512,0.00005209852,0.0002558897,0.000007978862,0.00001085865,0.0001139558,0.00003006611,0.973793,0.005663102,0.01932621,0.0007227764,0.000008540156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06440768,0.0004468138,0.9273527,0.001463574,0.00007720292,0.00009999234,0.0006213346,0.002760865,0.002769872],"genre_scores_gemma":[0.8457878,0.0002851474,0.1458498,0.0004941698,0.00007456437,0.00008745036,0.001094768,0.0001834263,0.006142785],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002876519,"threshold_uncertainty_score":0.01021129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01857445252678108,"score_gpt":0.3149303193573083,"score_spread":0.2963558668305272,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}