{"id":"W2941578761","doi":"10.1109/access.2019.2906605","title":"Segmenting Hemorrhagic and Ischemic Infarct Simultaneously From Follow-Up Non-Contrast CT Images in Patients With Acute Ischemic Stroke","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Segmentation; Artificial intelligence; Medicine; Convolutional neural network; Context (archaeology); Pattern recognition (psychology); Image segmentation; Computer science; Stroke (engine); Similarity measure; Radiology","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":[0.0005602607,0.0005361951,0.0005942879,0.001374712,0.0002406218,0.001110386,0.0004414193,0.0007171117,0.0005062587],"category_scores_gemma":[0.002119125,0.0003042232,0.0004394364,0.0005636576,0.0002920047,0.0005119455,0.0005751109,0.0003102636,0.0002444168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002243137,"about_ca_system_score_gemma":0.0004907858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00225117,"about_ca_topic_score_gemma":0.004655307,"domain_scores_codex":[0.9996549,0.00008226692,0.00005352256,0.00008317072,0.00008750598,0.00003871654],"domain_scores_gemma":[0.9995839,0.0001258434,0.0001148648,0.00005478552,0.00008376643,0.00003679869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003362573,0.000509865,0.1093858,0.0005721258,0.0005006102,0.002801837,0.0008386846,0.07740644,0.08024776,0.001894569,0.004257385,0.7182224],"study_design_scores_gemma":[0.0001068629,0.0007634236,0.1528853,0.0001014579,0.0004035959,0.005318155,0.0005089396,0.7650253,0.06744391,0.003389105,0.003930064,0.0001241003],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8290076,0.002100286,0.1651581,0.0002925668,0.00007708209,0.0002458933,0.0006035882,0.0007228681,0.001791941],"genre_scores_gemma":[0.9453865,0.0009133854,0.05157489,0.00007730307,0.00005719977,0.00008847402,0.001036754,0.00006717834,0.0007982226],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00225117,"threshold_uncertainty_score":0.00447607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005557997106553188,"score_gpt":0.236141071161876,"score_spread":0.2305830740553228,"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."}}