{"id":"W4413297862","doi":"10.1016/j.compbiomed.2025.110903","title":"Improving skull-stripping for infant MRI via weakly supervised domain adaptation using adversarial learning","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Fetal and Pediatric Neurological Disorders","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"Research Services, University of Calgary","keywords":"Adversarial system; Stripping (fiber); Skull; Artificial intelligence; Computer science; Domain (mathematical analysis); Adaptation (eye); Machine learning; Domain adaptation; Supervised learning; Pattern recognition (psychology); Computer vision; Psychology; Mathematics; Medicine; Neuroscience; Anatomy; Materials science; Artificial neural network","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":[0.001415358,0.001481539,0.0008024169,0.0007146874,0.0003295492,0.0007553495,0.001279924,0.001082326,0.001956264],"category_scores_gemma":[0.003721573,0.0005028261,0.001255559,0.000431912,0.0008652271,0.0008852991,0.001664554,0.002197125,0.001430334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004902194,"about_ca_system_score_gemma":0.0008959754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003355261,"about_ca_topic_score_gemma":0.004064627,"domain_scores_codex":[0.9995191,0.0001375318,0.00002507489,0.0001475812,0.0001265413,0.00004418],"domain_scores_gemma":[0.9987859,0.0005647955,0.0001284028,0.0002757699,0.0001741307,0.00007106856],"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":[0.0002244649,0.00009597292,0.002525148,0.0001680296,0.0001597324,0.000402587,0.0001849254,0.6806241,0.03129365,0.005142771,0.009060519,0.2701181],"study_design_scores_gemma":[0.000005687089,0.00003814141,0.0003085498,0.00001623474,0.00001589478,0.0001959806,0.0000247245,0.9883634,0.00696299,0.0026745,0.001380133,0.00001363414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02499471,0.0005590726,0.9696547,0.0002972102,0.00008677384,0.00005766382,0.0002066796,0.002622304,0.001520766],"genre_scores_gemma":[0.5200297,0.001312621,0.4664962,0.001065032,0.000120353,0.0002105302,0.002170321,0.0008599423,0.007735294],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003355261,"threshold_uncertainty_score":0.007485211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01869644503909518,"score_gpt":0.3012063069826379,"score_spread":0.2825098619435427,"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."}}