{"id":"W4282962995","doi":"10.1038/s41597-022-01401-7","title":"A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":149,"is_retracted":false,"has_abstract":true,"ca_institutions":"Research Institute for Aging; Heart and Stroke Foundation; University of Waterloo; Sunnybrook Health Science Centre; Ontario Brain Institute; University of Toronto; University of British Columbia","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Neurological Disorders and Stroke; Medical Research Council; National Institute of General Medical Sciences; Wellcome Trust; U.S. Department of Veterans Affairs","keywords":"Generalizability theory; Segmentation; Computer science; Artificial intelligence; Neuroimaging; Atlas (anatomy); Pattern recognition (psychology); Stroke (engine); Machine learning; Medicine; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["open_science"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.006115377,0.00242522,0.001883563,0.005143421,0.001779385,0.002983947,0.003544753,0.002502169,0.01329546],"category_scores_gemma":[0.02557747,0.0007929988,0.002484044,0.004669136,0.001018811,0.002291837,0.003557612,0.002566619,0.01807283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00199668,"about_ca_system_score_gemma":0.00546304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01693151,"about_ca_topic_score_gemma":0.03640953,"domain_scores_codex":[0.995645,0.0008209426,0.0007849007,0.001453398,0.00101157,0.0002841505],"domain_scores_gemma":[0.9892973,0.003147347,0.0008642033,0.003262174,0.002953397,0.000475583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000949389,0.0006041335,0.01960834,0.003539988,0.0009490201,0.0006642142,0.0005762145,0.01011923,0.009748481,0.003609368,0.7664796,0.1831521],"study_design_scores_gemma":[0.00123103,0.0006009301,0.08778549,0.002013234,0.001083253,0.003393831,0.0008419876,0.0596343,0.02673354,0.02815184,0.7879608,0.0005698602],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.06313531,0.004576469,0.1269674,0.002903154,0.001701726,0.002289603,0.7443144,0.04143211,0.01267991],"genre_scores_gemma":[0.03402878,0.0007356668,0.08418107,0.0006717822,0.0002462615,0.002110141,0.8715461,0.003572583,0.00290766],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9964553,"threshold_uncertainty_score":0.04447776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06612173964472086,"score_gpt":0.3552075638803168,"score_spread":0.2890858242355959,"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."}}