{"id":"W1972617227","doi":"10.1002/mrm.10436","title":"Automatic segmentation of the brain and intracranial cerebrospinal fluid in <i>T</i><sub>1</sub>‐weighted volume MRI scans of the head, and its application to serial cerebral and intracranial volumetry","year":2003,"lang":"en","type":"article","venue":"Magnetic Resonance in Medicine","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Glasgow","keywords":"Cerebrospinal fluid; Nuclear medicine; Segmentation; White matter; Brain size; Partial volume; Medicine; Magnetic resonance imaging; Context (archaeology); Epilepsy; Reproducibility; Radiology; Chemistry; Pathology; Computer science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009246707,0.0001670497,0.0003230693,0.0001479634,0.00006231209,0.00002268599,0.0003659389,0.00008899659,0.00003391254],"category_scores_gemma":[0.0004996867,0.0001172699,0.0000187041,0.0009241713,0.0003760099,0.0001845263,0.0001536767,0.0002007032,0.000001084555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005350942,"about_ca_system_score_gemma":0.00007518748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001877304,"about_ca_topic_score_gemma":0.0002214659,"domain_scores_codex":[0.9978707,0.0003409635,0.0006635908,0.0003863014,0.0005117194,0.0002267672],"domain_scores_gemma":[0.9991475,0.0001551635,0.0001941394,0.0003370675,0.0000739834,0.00009211687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000543462,0.00009212035,0.02703799,0.0002011542,0.000003362868,0.000003840567,0.002157499,0.000006652569,0.319465,0.0005352536,0.0005116605,0.6499311],"study_design_scores_gemma":[0.004004002,0.0009119756,0.7849696,0.0008032057,0.00002122016,0.00007711544,0.000188827,0.125126,0.08185389,0.001635376,0.000174219,0.000234575],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9467582,0.00106241,0.0472856,0.003447533,0.0001493537,0.001234125,0.000005948715,0.00002265137,0.00003416815],"genre_scores_gemma":[0.978798,0.0001638381,0.02007554,0.0007722585,0.00005642057,0.00009292525,0.000001721879,0.00001173311,0.00002756522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7579316,"threshold_uncertainty_score":0.4782127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006015390230942236,"score_gpt":0.2463838372885456,"score_spread":0.2403684470576034,"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."}}