{"id":"W4405022246","doi":"10.1109/access.2024.3511430","title":"Adaptive Asynchronous Split Federated Learning for Medical Image Segmentation","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Image segmentation; Asynchronous communication; Artificial intelligence; Computer vision; Segmentation; Image (mathematics); Asynchronous learning; Computer network; Synchronous learning; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002081032,0.0004356636,0.0005988699,0.00048626,0.0005121544,0.0008110536,0.001405936,0.001062546,0.001318428],"category_scores_gemma":[0.005235212,0.0002430224,0.0003172676,0.0005460802,0.0008282177,0.001924383,0.001413208,0.001022313,0.0003549326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008725193,"about_ca_system_score_gemma":0.001130971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002014275,"about_ca_topic_score_gemma":0.002279867,"domain_scores_codex":[0.9990859,0.0003485599,0.00004279502,0.0002308483,0.0001869853,0.0001049855],"domain_scores_gemma":[0.9983365,0.0007513516,0.0001318246,0.0004305644,0.0002519141,0.00009784834],"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":[0.001074119,0.0002948812,0.003677711,0.000110934,0.00007187892,0.0002520524,0.0002723303,0.5966592,0.01591993,0.01751394,0.005526,0.3586271],"study_design_scores_gemma":[0.00001036242,0.00002930562,0.0001652736,0.00000281753,0.000003834647,0.0000305085,0.000012897,0.9899917,0.002294061,0.006963687,0.0004914789,0.000004062799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02806869,0.0001921247,0.9691366,0.0002785254,0.00003149195,0.0000347245,0.00003975515,0.001360667,0.0008574073],"genre_scores_gemma":[0.8608928,0.0001161134,0.1370123,0.0002646259,0.00003843015,0.00007106915,0.0001424984,0.00008021142,0.001381989],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002081032,"threshold_uncertainty_score":0.0110057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03997759046979889,"score_gpt":0.3469665405618829,"score_spread":0.306988950092084,"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."}}