{"id":"W4398784948","doi":"10.1016/j.compbiomed.2024.108646","title":"Privacy-preserving blockchain-based federated learning for brain tumor segmentation","year":2024,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Masking (illustration); Data sharing; Blockchain; Artificial intelligence; Asynchronous communication; Information privacy; Health care; Segmentation; Quality (philosophy); Machine learning; Computer security; Computer network; Medicine","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":[0.000363944,0.00008175512,0.0001136986,0.0001662757,0.0001405002,0.00001878413,0.00007925079,0.00004547221,0.00001989598],"category_scores_gemma":[0.0008110021,0.00006629727,0.00001526458,0.000224116,0.0001385901,0.00001657735,0.00002622704,0.0001549092,0.000002186177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003106171,"about_ca_system_score_gemma":0.00002368925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008041326,"about_ca_topic_score_gemma":0.000004963177,"domain_scores_codex":[0.9991747,0.0001681989,0.0001640383,0.0003135739,0.00004188143,0.0001376772],"domain_scores_gemma":[0.9986877,0.001157774,0.00003840486,0.00006364154,0.0000137319,0.00003876245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008792539,0.00002245237,0.0009797397,0.0001343761,0.000005079974,0.00001670709,0.0007846577,0.0003817547,0.9279634,0.004685141,0.001933592,0.06300519],"study_design_scores_gemma":[0.001398899,0.0004701479,0.001678841,0.0002355541,0.000006971026,0.00003534305,0.0001946664,0.9366857,0.04424114,0.002894289,0.0120348,0.0001236216],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8380631,0.0002939004,0.1359628,0.0235908,0.001241497,0.0004094929,0.000001716654,0.0002086933,0.0002280643],"genre_scores_gemma":[0.9953769,0.000008480521,0.0005931791,0.003679753,0.0001353547,0.00003862213,0.00001178782,0.000007870549,0.0001479941],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.936304,"threshold_uncertainty_score":0.2703524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03906540659915875,"score_gpt":0.3368969249965982,"score_spread":0.2978315183974394,"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."}}