{"id":"W3214419888","doi":"10.1016/j.compbiomed.2021.105033","title":"Evaluating nnU-Net for early ischemic change segmentation on non-contrast computed tomography in patients with Acute Ischemic Stroke","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hotchkiss Brain Institute; Foothills Medical Centre; University of Calgary; Circle Cardiovascular Imaging","funders":"Canadian Institutes of Health Research","keywords":"Segmentation; Medicine; Benchmark (surveying); Computer science; Intraclass correlation; Similarity (geometry); Ischemic stroke; Artificial intelligence; Computed tomography; Stroke (engine); Radiology; Cardiology; Ischemia; Image (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":[0.0002853492,0.0002456149,0.000554224,0.0003412225,0.00004368742,0.000005555571,0.0000934813,0.0001433655,0.00001191834],"category_scores_gemma":[0.00004464882,0.0001922861,0.00004028713,0.0003279958,0.0001725216,0.00005831255,0.00008243594,0.0002655865,0.000001129255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008153536,"about_ca_system_score_gemma":0.00003354342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002669699,"about_ca_topic_score_gemma":0.000009256175,"domain_scores_codex":[0.9985126,0.00005229202,0.0003762773,0.0005351199,0.0001683463,0.0003553945],"domain_scores_gemma":[0.9992024,0.0002103148,0.0001395538,0.0002287968,0.0001204526,0.00009846976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002284636,0.000368622,0.8895898,0.000219325,0.0005140842,0.0000786036,0.00148119,0.000006180503,0.0347204,0.0000395226,0.008250598,0.06244707],"study_design_scores_gemma":[0.03832229,0.00568006,0.9412802,0.001664348,0.0003469892,0.00002686668,0.0002948993,0.003912501,0.007007313,0.00002326358,0.001101413,0.0003398035],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9886119,0.0003223655,0.007276409,0.001311556,0.000371907,0.001382286,0.00002630843,0.00002861686,0.0006686159],"genre_scores_gemma":[0.972991,0.0000616848,0.0223572,0.003190009,0.0002629372,0.0001604102,0.0009012024,0.00002133118,0.00005424436],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06210726,"threshold_uncertainty_score":0.7841198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02386480425467633,"score_gpt":0.3211373827315584,"score_spread":0.297272578476882,"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."}}