{"id":"W4416054896","doi":"10.59275/j.melba.2025-d1g3","title":"Investigating Demographic Bias in Brain MRI Segmentation: A Comparative Study of Deep-Learning and Non-Deep-Learning Methods","year":2025,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; McDonnell Center for Systems Neuroscience; National Institutes of Health","keywords":"Segmentation; Metric (unit); Scale-space segmentation; Pattern recognition (psychology); Image segmentation; Field (mathematics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007747565,0.0004204038,0.0009933891,0.0009899376,0.0005765837,0.0001547433,0.001338476,0.0001207841,0.000003894942],"category_scores_gemma":[0.002036585,0.0003286311,0.0001860004,0.001584075,0.000407053,0.0003038163,0.00166818,0.004344899,3.180447e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009633812,"about_ca_system_score_gemma":0.0001236826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008132483,"about_ca_topic_score_gemma":0.00002479737,"domain_scores_codex":[0.9934167,0.003369368,0.001576703,0.0005306837,0.000661741,0.0004448112],"domain_scores_gemma":[0.9891569,0.007372493,0.002607641,0.0003234622,0.0003342431,0.0002052453],"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":[0.00009756805,0.0003862976,0.08879781,0.0004340361,0.0004067424,0.00001859863,0.0425129,0.4574753,0.003778163,0.0002344901,0.00004561116,0.4058124],"study_design_scores_gemma":[0.001692032,0.0004947281,0.005409052,0.0006955546,0.0001443916,0.00007327692,0.004654645,0.9822826,0.0001423734,0.003514026,0.0006093117,0.0002879594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1094119,0.002318716,0.8838187,0.003305891,0.0002203351,0.0008147105,0.000001207318,0.00005956954,0.0000489981],"genre_scores_gemma":[0.6607477,0.0002232648,0.3386584,0.0001406148,0.0001156589,0.00004550551,0.00001196041,0.0000236667,0.00003316078],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5513359,"threshold_uncertainty_score":0.9999166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03975856399701808,"score_gpt":0.3976833927445126,"score_spread":0.3579248287474945,"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."}}