{"id":"W4393114969","doi":"10.1016/j.compmedimag.2024.102376","title":"Annotation-free prediction of treatment-specific tissue outcome from 4D CT perfusion imaging in acute ischemic stroke","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hotchkiss Brain Institute; Alberta Children's Hospital; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Calgary Foundation","keywords":"Perfusion; Thrombolysis; Artificial intelligence; Computer science; Stroke (engine); Perfusion scanning; Medicine; Binary classification; Radiology; Probabilistic logic; Pattern recognition (psychology); Machine learning; Myocardial infarction; Cardiology","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":[0.0002895298,0.0002732391,0.0005015166,0.0004596988,0.00006432022,0.00007504789,0.0001843449,0.00006337385,0.0000858345],"category_scores_gemma":[0.00007256674,0.0002299259,0.0001244049,0.0003640196,0.0003137567,0.0001563698,0.0002235401,0.0003691933,0.000004347467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001187831,"about_ca_system_score_gemma":0.0001042442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001832692,"about_ca_topic_score_gemma":0.000003055805,"domain_scores_codex":[0.9979278,0.00004822694,0.0006309022,0.0005578632,0.0005338649,0.000301373],"domain_scores_gemma":[0.9989671,0.0002208054,0.00008373729,0.0004354395,0.0000559782,0.0002369985],"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":[0.0002392011,0.000328563,0.2186368,0.0003861756,0.0004081429,0.002710232,0.00142566,0.000003335182,0.1072836,0.0003639743,0.04081817,0.6273961],"study_design_scores_gemma":[0.01830834,0.0004080603,0.08462092,0.003553075,0.001171472,0.0009657576,0.0006730751,0.5805936,0.009566469,0.000387268,0.299047,0.0007049171],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9275499,0.007586611,0.0551907,0.006946164,0.001086561,0.0004540693,0.0002257272,0.0002763532,0.0006838966],"genre_scores_gemma":[0.9862241,0.003871487,0.008175021,0.0005974663,0.0003989022,0.00002989935,0.0004475326,0.00004656731,0.0002090861],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6266912,"threshold_uncertainty_score":0.9376107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0150491530456705,"score_gpt":0.2823902842144167,"score_spread":0.2673411311687462,"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."}}