{"id":"W3142621654","doi":"10.1101/2021.03.29.437045","title":"ID-Seg: An Accurate and Reliable Infant Deep learning Segmentation Framework for Limbic Structures","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neonatal and fetal brain pathology","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institutes of Health","keywords":"Neuroimaging; Segmentation; Amygdala; Hippocampus; Limbic system; Artificial intelligence; Magnetic resonance imaging; Computer science; Pattern recognition (psychology); Neuroscience; Psychology; Medicine; Radiology; Central nervous system","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0008789338,0.001601825,0.0008380441,0.001064546,0.0003503551,0.000829586,0.002206134,0.001269718,0.001976502],"category_scores_gemma":[0.001850277,0.0005418342,0.001120126,0.0005813515,0.0004344754,0.0007523496,0.001296729,0.001440692,0.001095132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001017092,"about_ca_system_score_gemma":0.001811655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01192713,"about_ca_topic_score_gemma":0.02191055,"domain_scores_codex":[0.9996279,0.00005912666,0.0000224655,0.0001306467,0.00009988921,0.00005988584],"domain_scores_gemma":[0.9996364,0.00008993642,0.00004408804,0.00005392581,0.0001405366,0.00003507627],"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":[0.0004456817,0.0002217879,0.008311211,0.0002729271,0.0003119001,0.0003274648,0.0001553938,0.3551235,0.03824026,0.004592693,0.02551519,0.566482],"study_design_scores_gemma":[0.00001275465,0.00007088191,0.0008063383,0.00001722265,0.0000217648,0.00006823022,0.00002178129,0.9868557,0.008296592,0.001853923,0.001960704,0.00001417349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08519463,0.001857734,0.8878846,0.0005018308,0.0001522356,0.0001851128,0.002882018,0.01922036,0.002121405],"genre_scores_gemma":[0.4375415,0.0008659685,0.5389302,0.0007529361,0.00007624605,0.0004240374,0.01203938,0.001192277,0.008177484],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01192713,"threshold_uncertainty_score":0.02371544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01580415595197576,"score_gpt":0.2650012829386819,"score_spread":0.2491971269867061,"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."}}