{"id":"W4401557770","doi":"10.1002/nbm.5227","title":"Automatic deep learning segmentation of the hippocampus on high‐resolution diffusion magnetic resonance imaging and its application to the healthy lifespan","year":2024,"lang":"en","type":"article","venue":"NMR in Biomedicine","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"MacEwan University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canada Foundation for Innovation; University Hospital Foundation; Ministry of Advanced Education, Government of Alberta; Women and Children's Health Research Institute; Children's Health Research Institute","keywords":"Fractional anisotropy; Diffusion MRI; Magnetic resonance imaging; Segmentation; Artificial intelligence; Hippocampus; Computer science; Sørensen–Dice coefficient; Voxel; Population; Pattern recognition (psychology); Image segmentation; Neuroscience; Medicine; Psychology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001005645,0.0006443586,0.000430394,0.0008930396,0.0002576866,0.0004391912,0.0005291901,0.0007078976,0.0007113626],"category_scores_gemma":[0.002445776,0.0002714749,0.0005495502,0.0003341384,0.000330398,0.0004255938,0.0006589759,0.0003886309,0.0002917959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000408769,"about_ca_system_score_gemma":0.0006464272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007280047,"about_ca_topic_score_gemma":0.01071777,"domain_scores_codex":[0.9997209,0.00007371576,0.00001824217,0.0001139211,0.00004161824,0.00003167995],"domain_scores_gemma":[0.999413,0.0001913546,0.00009089029,0.0001012617,0.00017068,0.0000327835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007948034,0.0002560217,0.02697067,0.0002534554,0.0003396094,0.0004828416,0.0004488206,0.1490261,0.1043137,0.001906624,0.004070032,0.7111374],"study_design_scores_gemma":[0.00004273008,0.0002607648,0.0274117,0.00005090308,0.00007290299,0.0004632765,0.00008246201,0.9355335,0.03103153,0.003130445,0.001873181,0.00004656172],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7512668,0.001378959,0.2429344,0.0003056695,0.00008610392,0.0001183562,0.0007977795,0.001593011,0.001518864],"genre_scores_gemma":[0.8835688,0.0002848636,0.1134867,0.00006537295,0.0000295959,0.00007111281,0.0006831841,0.00008792833,0.001722489],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007280047,"threshold_uncertainty_score":0.01447535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01707156841037956,"score_gpt":0.3269405340313867,"score_spread":0.3098689656210071,"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."}}