{"id":"W2980934859","doi":"10.1002/hbm.24811","title":"Hippocampal segmentation for brains with extensive atrophy using three‐dimensional convolutional neural networks","year":2019,"lang":"en","type":"article","venue":"Human Brain Mapping","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":83,"is_retracted":false,"has_abstract":true,"ca_institutions":"Heart and Stroke Foundation; University of Toronto; Ontario Brain Institute; Sunnybrook Health Science Centre","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; H. Lundbeck A/S; National Institute on Aging; Fujirebio Europe; Pfizer; Novartis Pharmaceuticals Corporation; AbbVie; Takeda Pharmaceutical Company; Bristol-Myers Squibb; Eli Lilly and Company; Servier; GE Healthcare; BioClinica; Norman Cousins Center for Psychoneuroimmunology; Alzheimer's Drug Discovery Foundation; Biogen","keywords":"Computer science; Atrophy; Convolutional neural network; Artificial intelligence; Segmentation; Sørensen–Dice coefficient; Dementia; Pattern recognition (psychology); Correlation; Medicine; Pathology; Disease; Image segmentation; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002329271,0.0002134284,0.0001937513,0.0001571084,0.0007191388,0.0001046071,0.0001523035,0.000079093,0.0001795525],"category_scores_gemma":[0.0001098314,0.0002055456,0.0001007808,0.0002996734,0.0001659062,0.0003055373,0.00004187733,0.0002114606,0.00002644367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001530262,"about_ca_system_score_gemma":0.00005244504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009005544,"about_ca_topic_score_gemma":0.0000153109,"domain_scores_codex":[0.9982265,0.0001268258,0.0002953113,0.000615798,0.0003497034,0.0003859187],"domain_scores_gemma":[0.9988458,0.0004331039,0.0002518128,0.0002441713,0.0001335846,0.00009153787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001124362,0.00003783136,0.001279024,0.00002623628,0.00001205213,0.000004637251,0.0001430371,0.03720713,0.9507396,0.009460449,0.0003872506,0.0005903369],"study_design_scores_gemma":[0.002131387,0.0002686184,0.04280612,0.00005746767,0.00001440729,0.0001310632,0.0002658084,0.9491376,0.002252324,0.001937399,0.0005772481,0.0004205763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8749223,0.00001420198,0.1227053,0.0006856131,0.0004165001,0.0009225956,0.00001161519,0.0001293986,0.0001923648],"genre_scores_gemma":[0.9937569,2.517901e-7,0.001574712,0.003852734,0.0003062977,0.0000564079,0.00004508018,0.00003985358,0.0003676908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9484872,"threshold_uncertainty_score":0.8381906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06268423052243269,"score_gpt":0.2818773216889248,"score_spread":0.2191930911664921,"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."}}