{"id":"W7017167564","doi":"","title":"Accurate and robust automated segmentation in T1-weighted magnetic resonance imaging of the human brain","year":2020,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Genentech; U.S. Food and Drug Administration; Eisai; Synarc; Novartis; Elan; Medpace; GlaxoSmithKline; Pfizer; National Institutes of Health; Canada First Research Excellence Fund; AstraZeneca; Eli Lilly and Company; Bristol-Myers Squibb","keywords":"Convolutional neural network; Segmentation; Robustness (evolution); Human brain; Pattern recognition (psychology); Image segmentation; Deep learning; 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":[0.001496649,0.0006849255,0.0003921003,0.001142743,0.0004599484,0.001850999,0.0007806289,0.001309181,0.004499371],"category_scores_gemma":[0.003433162,0.0006501972,0.0005759886,0.0005964411,0.0006350796,0.001148544,0.00112181,0.001209444,0.003359178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005584679,"about_ca_system_score_gemma":0.001521854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002702652,"about_ca_topic_score_gemma":0.005777208,"domain_scores_codex":[0.9993021,0.0001361878,0.00003558339,0.0001911676,0.0002757112,0.00005926215],"domain_scores_gemma":[0.9990056,0.0003571651,0.0001111254,0.0002253904,0.0002698292,0.00003092266],"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":[0.0001809379,0.0001042807,0.001877903,0.0007388908,0.0001353393,0.0003323067,0.0005360783,0.03530788,0.2040073,0.01290088,0.03022335,0.7136549],"study_design_scores_gemma":[0.00005943701,0.0002531529,0.02010277,0.0004950719,0.0001625202,0.002681452,0.0003023655,0.4770341,0.3730908,0.02293796,0.1026864,0.000194058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04001829,0.002979703,0.9412115,0.001469411,0.0002941741,0.000297761,0.0005179826,0.00164579,0.01156526],"genre_scores_gemma":[0.1636625,0.004362801,0.8003651,0.0005365789,0.0003731676,0.0003396175,0.001707649,0.001179496,0.02747315],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004499371,"threshold_uncertainty_score":0.0150519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0271225561313362,"score_gpt":0.2644000408591242,"score_spread":0.237277484727788,"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."}}