{"id":"W2984254165","doi":"10.1016/j.compmedimag.2019.101660","title":"Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation","year":2020,"lang":"","type":"article","venue":"Espace ÉTS (ETS)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":129,"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":"Artificial intelligence; Computer science; Segmentation; Convolutional neural network; Pattern recognition (psychology); Partial volume; White matter; Ranking (information retrieval); Deep learning; Image segmentation; 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":[0.0002097705,0.0004271201,0.0003854349,0.000122918,0.0007722145,0.0003671689,0.0005620081,0.0001383689,0.00002755944],"category_scores_gemma":[0.0004229187,0.0004774813,0.000114143,0.001241669,0.0002324882,0.001055128,0.0003687322,0.0002916411,0.0000919229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008627548,"about_ca_system_score_gemma":0.0001393778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001190885,"about_ca_topic_score_gemma":0.0001045618,"domain_scores_codex":[0.997114,0.0001573771,0.0005159971,0.001233764,0.0003531806,0.0006256767],"domain_scores_gemma":[0.9968284,0.001442511,0.0004144544,0.0005364505,0.0002944129,0.0004837991],"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":[0.0006252817,0.0004738314,0.002413234,0.0005040331,0.0003555385,0.00005083719,0.1002127,0.2015125,0.07621511,0.1880636,0.05812405,0.3714492],"study_design_scores_gemma":[0.001485444,0.0005534333,0.003128214,0.00006502288,0.00008121711,0.00001866171,0.001124652,0.948087,0.006626786,0.004316364,0.03380331,0.0007099078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01008291,0.0009470378,0.8707875,0.1155641,0.000236127,0.002004562,0.00006279673,0.0001757033,0.0001392765],"genre_scores_gemma":[0.6733725,0.0006266398,0.31389,0.009746761,0.0006463029,0.0007847527,0.00009800349,0.00008363162,0.0007514135],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7465745,"threshold_uncertainty_score":0.9997677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02001396620956352,"score_gpt":0.2857617108607975,"score_spread":0.265747744651234,"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."}}