{"id":"W4389776620","doi":"10.1109/tnnls.2023.3338867","title":"Hypernetwork-Based Physics-Driven Personalized Federated Learning for CT Imaging","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Sichuan Province Science and Technology Support Program; National Natural Science Foundation of China","keywords":"Computer science; Hyperparameter; Data sharing; Domain (mathematical analysis); Artificial intelligence; Deep learning; Protocol (science); Machine learning; Data science; Medical physics; Medicine; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000355605,0.0002297998,0.0003792369,0.0001039637,0.0008943638,0.0001334535,0.00006461125,0.00006362994,0.00001822042],"category_scores_gemma":[0.00002080736,0.0002039219,0.0001739183,0.0004604241,0.0001099016,0.00006045211,0.00000179075,0.0009409864,0.000009554031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004045821,"about_ca_system_score_gemma":0.00002984527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006796461,"about_ca_topic_score_gemma":0.00000125785,"domain_scores_codex":[0.9984732,0.0001666233,0.0002992902,0.00041518,0.0002193383,0.0004263376],"domain_scores_gemma":[0.9989744,0.0004720913,0.0001123296,0.0001411754,0.00009753287,0.0002025104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001047358,0.00005528551,0.0009126656,0.0001228776,0.00005092624,0.00002174434,0.00005111098,0.9574001,0.0008576949,0.00003681768,0.002001413,0.03838466],"study_design_scores_gemma":[0.001190235,0.000192442,0.00008955436,0.000320293,0.0001113561,0.00005867522,0.0001543579,0.9834002,0.0000897628,0.000003246028,0.0141923,0.0001976178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05923066,0.0001667518,0.9363261,0.001779423,0.0003491158,0.0008845428,0.000003943408,0.001198243,0.00006117208],"genre_scores_gemma":[0.9953975,0.00009998754,0.0004423017,0.0003210227,0.0004014802,0.0004275029,0.00007289855,0.00007166765,0.002765616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9361669,"threshold_uncertainty_score":0.8315694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02722588357076922,"score_gpt":0.2912125022357203,"score_spread":0.263986618664951,"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."}}