{"id":"W2775394473","doi":"10.1016/j.compmedimag.2019.101660","title":"Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation","year":2019,"lang":"en","type":"preprint","venue":"Computerized Medical Imaging and Graphics","topic":"Neonatal and fetal brain pathology","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Computer science; Segmentation; Artificial intelligence; Pattern recognition (psychology); Partial volume; White matter; Image segmentation; Limiting; Machine learning; Magnetic resonance imaging; Medicine; Radiology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004503819,0.0002915697,0.0006105037,0.000248896,0.0001266462,0.00005977566,0.000104023,0.0002888489,0.000008570565],"category_scores_gemma":[0.0004158753,0.0002531479,0.0001245479,0.0001074515,0.0005210636,0.00005618277,0.0004106805,0.0006541212,0.000001868032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001593393,"about_ca_system_score_gemma":0.0001689803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002590199,"about_ca_topic_score_gemma":0.000005090712,"domain_scores_codex":[0.9983094,0.00008876583,0.0003864289,0.0006275373,0.0003048735,0.0002830029],"domain_scores_gemma":[0.9982221,0.00087411,0.0001534132,0.0002401754,0.0001714699,0.0003387348],"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":[0.001647357,0.0006534117,0.03241669,0.01062377,0.001091096,0.00106794,0.00921113,0.00008213861,0.008456097,0.01160943,0.01577615,0.9073648],"study_design_scores_gemma":[0.01581058,0.0007155872,0.06410309,0.003337067,0.0007937773,0.002287111,0.0006696471,0.853735,0.0003435629,0.03635158,0.02057611,0.001276854],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1487872,0.005906905,0.8058236,0.03614611,0.001307696,0.001643201,0.0001102537,0.0001629296,0.0001120676],"genre_scores_gemma":[0.8069791,0.008021671,0.1357964,0.04243817,0.001463289,0.0004731092,0.004242243,0.0001594235,0.0004266045],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9060879,"threshold_uncertainty_score":0.9999921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01362707681164554,"score_gpt":0.2991535171374735,"score_spread":0.2855264403258279,"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."}}