{"id":"W4226082367","doi":"10.1038/s41598-022-05539-7","title":"Federated learning and differential privacy for medical image analysis","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":316,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Vector Institute; MaRS; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario; Compute Canada","keywords":"Computer science; Confidentiality; Differential privacy; Federated learning; Machine learning; Support vector machine; Artificial intelligence; Scale (ratio); Data science; Data mining; Computer security","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002783557,0.0001401672,0.000256966,0.0004946492,0.001745032,0.001200203,0.006147621,0.00006305885,0.0003376829],"category_scores_gemma":[0.02007736,0.0001345725,0.0001192826,0.002040733,0.0002678915,0.0004151662,0.07087807,0.0003572811,0.000002242178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006977833,"about_ca_system_score_gemma":0.0001848456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001832965,"about_ca_topic_score_gemma":0.000008057572,"domain_scores_codex":[0.9965338,0.0001274508,0.0004649875,0.001306962,0.00115242,0.0004144113],"domain_scores_gemma":[0.9957374,0.0001546903,0.0002984633,0.003554284,0.0001178496,0.0001373175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003192216,0.0005013042,0.03491994,0.00009418045,0.0008757979,0.002605213,0.0006354508,0.00009927459,0.03172804,0.001349137,0.8075926,0.1195671],"study_design_scores_gemma":[0.0003051085,0.00008267729,0.001314195,0.00000831379,0.0001013501,0.0003817163,0.00008715021,0.8142087,0.004972967,0.1064229,0.07173445,0.000380421],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2757845,0.0001052454,0.7111934,0.008078727,0.003494069,0.0003217032,0.000007089942,0.0008160766,0.0001992365],"genre_scores_gemma":[0.942918,0.000004087928,0.05603091,0.00003211146,0.0000246703,0.0001088095,0.0001512242,0.00001099817,0.0007191618],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8141095,"threshold_uncertainty_score":0.9998366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01722549929520773,"score_gpt":0.2850408209136559,"score_spread":0.2678153216184482,"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."}}