{"id":"W4221030494","doi":"10.1101/2022.03.10.22272216","title":"Semi-automatic segmentation of the fetal brain from Magnetic Resonance Imaging","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Fetal and Pediatric Neurological Disorders","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research; Canada First Research Excellence Fund","keywords":"Segmentation; Interquartile range; Magnetic resonance imaging; Artificial intelligence; Sørensen–Dice coefficient; Computer science; Affine transformation; Kappa; Wilcoxon signed-rank test; Pattern recognition (psychology); Nuclear medicine; Medicine; Radiology; Image segmentation; Mathematics; Surgery; Internal medicine; Mann–Whitney U test","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":[0.001935919,0.0005866102,0.0005315778,0.001905483,0.0003610771,0.001118225,0.0006531174,0.0005985153,0.002522679],"category_scores_gemma":[0.005950045,0.0003391789,0.0005776308,0.0008157759,0.0004546833,0.0006153408,0.0005949257,0.0003642558,0.001022704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004411959,"about_ca_system_score_gemma":0.001171996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003578803,"about_ca_topic_score_gemma":0.004944531,"domain_scores_codex":[0.9989731,0.000333032,0.0001266691,0.0001889255,0.0003195963,0.00005855976],"domain_scores_gemma":[0.9986631,0.0005789276,0.0002103707,0.0002384574,0.0002814166,0.0000277864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00139349,0.0001169745,0.01522817,0.0008796919,0.0002242679,0.0009572676,0.001176045,0.02190746,0.3905063,0.005440455,0.003503072,0.5586668],"study_design_scores_gemma":[0.0002261188,0.0011917,0.1709724,0.0004081168,0.0003004783,0.01174049,0.0009595508,0.3666775,0.4049987,0.01055728,0.03165979,0.0003078807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2681272,0.001601735,0.7221181,0.0001917286,0.00009526913,0.000514366,0.001228837,0.002709743,0.00341311],"genre_scores_gemma":[0.533493,0.0008514187,0.4612985,0.00008647411,0.00002843589,0.0003661299,0.001448117,0.0005127399,0.001915139],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003578803,"threshold_uncertainty_score":0.01023823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01339860201120846,"score_gpt":0.2537574300010214,"score_spread":0.2403588279898129,"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."}}