{"id":"W4308334508","doi":"10.3389/fnins.2022.1009654","title":"Predicting the tissue outcome of acute ischemic stroke from acute 4D computed tomography perfusion imaging using temporal features and deep learning","year":2022,"lang":"en","type":"article","venue":"Frontiers in Neuroscience","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Children's Hospital; Hotchkiss Brain Institute; University of Calgary","funders":"Canada Research Chairs; Heart and Stroke Foundation of Canada","keywords":"Thresholding; Perfusion; Artificial intelligence; Perfusion scanning; Convolutional neural network; Deep learning; Thrombolysis; Computer science; Pattern recognition (psychology); Stroke (engine); Nuclear medicine; Medicine; Radiology; Internal medicine; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000867792,0.0006882774,0.0004452524,0.0009910667,0.0001399145,0.0006894012,0.0004115597,0.0004041115,0.0005618117],"category_scores_gemma":[0.002775886,0.0002371242,0.000561608,0.000567087,0.00026475,0.0006530455,0.0006609449,0.0005501104,0.0002564437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005006703,"about_ca_system_score_gemma":0.0005977694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005015538,"about_ca_topic_score_gemma":0.008337761,"domain_scores_codex":[0.9998028,0.0000487217,0.00002180414,0.00006477046,0.00003798628,0.00002386961],"domain_scores_gemma":[0.9994727,0.0001943159,0.0001143638,0.00006434312,0.000116506,0.00003773133],"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":[0.001293303,0.0003748533,0.1391316,0.0003355197,0.0004332587,0.0006847715,0.0001407018,0.3588124,0.02348049,0.001492955,0.005390821,0.4684293],"study_design_scores_gemma":[0.00001819037,0.000149922,0.02123294,0.00003226177,0.00007708833,0.0002217071,0.00003475154,0.9667791,0.008491281,0.002154998,0.0007851968,0.00002256956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7526222,0.001940112,0.2378229,0.0006086384,0.00008908811,0.0001385669,0.003887694,0.001006282,0.001884454],"genre_scores_gemma":[0.9655125,0.0006045777,0.02967256,0.00008237109,0.0000454595,0.00007184459,0.00331334,0.00003655093,0.0006607408],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005015538,"threshold_uncertainty_score":0.009972692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00983492561510595,"score_gpt":0.2567638191751757,"score_spread":0.2469288935600698,"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."}}