{"id":"W1656023708","doi":"10.1007/s10044-015-0492-0","title":"Automated hippocampal segmentation in 3D MRI using random undersampling with boosting algorithm","year":2015,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; Alzheimer's Disease Neuroimaging Initiative; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Synarc; University of Southern California; Medpace; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; F. Hoffmann-La Roche; Alzheimer's Drug Discovery Foundation; University of California, San Francisco; Foundation for the National Institutes of Health","keywords":"Undersampling; Boosting (machine learning); Pattern recognition (psychology); Artificial intelligence; Segmentation; Computer science; Algorithm; Hippocampal formation; Random forest; Medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003903086,0.0001016334,0.0001855883,0.0003033178,0.00009400151,0.0001684409,0.0001821885,0.00003115457,0.00000733665],"category_scores_gemma":[0.000009175912,0.00008866537,0.00003003531,0.001319892,0.00004242488,0.0002737594,0.00006526636,0.0000755988,0.000003553269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000714194,"about_ca_system_score_gemma":0.00003971697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004836211,"about_ca_topic_score_gemma":0.00009841025,"domain_scores_codex":[0.9989322,0.00006928346,0.0002742727,0.0003233176,0.000249742,0.0001512133],"domain_scores_gemma":[0.9993424,0.00007455144,0.0001398499,0.0002357029,0.00008548939,0.0001220415],"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":[0.000004798117,0.0001312437,0.04564197,0.00001969518,0.0002479769,0.000007240148,0.001480999,0.008842665,0.001885606,0.00006405346,0.00005172752,0.941622],"study_design_scores_gemma":[0.000649152,0.00001376091,0.001821716,0.00001359013,0.0001120075,0.000004354361,0.0002980626,0.994903,0.001855596,0.0001959666,0.00001350157,0.0001193283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003987968,0.00003934693,0.9952041,0.0001747394,0.000006877032,0.0002890641,0.000003541965,0.0002564341,0.00003794632],"genre_scores_gemma":[0.3015001,0.00001247612,0.6979319,0.0003412213,0.00002457272,0.0001273347,0.00004864387,0.000006828278,0.000006894928],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9860603,"threshold_uncertainty_score":0.3615669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03224919150146756,"score_gpt":0.3183575597015484,"score_spread":0.2861083682000808,"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."}}