{"id":"W4417131379","doi":"10.1109/jbhi.2025.3622934","title":"Federated Pseudo-Labeling: A Data-Centric, Privacy-Preserving Framework for Medical Image Segmentation","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Scalability; Segmentation; Pyramid (geometry); Raw data; Block (permutation group theory); Federated learning; Annotation; Deep learning; Convolutional neural network","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":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00463849,0.0001765533,0.0004673375,0.0004518086,0.0003506083,0.0003489172,0.01373063,0.00030045,0.00001265795],"category_scores_gemma":[0.03073241,0.0001362525,0.00004881282,0.0007944476,0.0001893659,0.001591886,0.01799821,0.0007977863,0.000003181588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001427825,"about_ca_system_score_gemma":0.001417527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001266059,"about_ca_topic_score_gemma":0.000002120498,"domain_scores_codex":[0.9961997,0.00007277624,0.002028697,0.0001900388,0.001007812,0.0005009993],"domain_scores_gemma":[0.9952894,0.0008224717,0.001126947,0.001997504,0.0003118085,0.0004518018],"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":[0.000034217,0.0001737398,0.0001328522,0.001201994,0.0001000913,0.0000150161,0.0004231407,8.961939e-7,0.00004275532,0.001782475,0.6888925,0.3072003],"study_design_scores_gemma":[0.001859009,0.0003980389,0.0001008131,0.001373917,0.00002331672,0.000147773,0.0003512468,0.8442966,0.0002796765,0.1261862,0.02480205,0.0001813882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001636216,0.0005199098,0.811235,0.1850703,0.001135753,0.0002517896,0.00003823844,0.00008997044,0.00002289297],"genre_scores_gemma":[0.002966353,0.002562329,0.9883676,0.005864124,0.0001822108,0.000005888749,0.00003862048,0.000006974426,0.000005934931],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8442957,"threshold_uncertainty_score":0.9916056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06258769968338175,"score_gpt":0.3855086487173895,"score_spread":0.3229209490340078,"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."}}