{"id":"W4413093915","doi":"10.1038/s41467-025-62373-x","title":"DeepISLES: a clinically validated ischemic stroke segmentation model from the ISLES'22 challenge","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"National Institute of Neurological Disorders and Stroke; Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Vlaamse regering; KU Leuven; Ministry of Trade, Industry and Energy; Schweizerische Herzstiftung; National Research Foundation; Korea Evaluation Institute of Industrial Technology; Pohang University of Science and Technology; National Research Foundation of Korea; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Helmut Horten Stiftung; National Science Foundation","keywords":"Ischemic stroke; Stroke (engine); Segmentation; Computer science; Medicine; Computational biology; Internal medicine; Cardiology; Bioinformatics; Artificial intelligence; Biology; Ischemia; Physics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.004314669,0.002815364,0.001670773,0.002744047,0.001114795,0.002997853,0.003038242,0.003273681,0.004306039],"category_scores_gemma":[0.0110145,0.0008353183,0.002156887,0.001463654,0.0007844241,0.001267221,0.002798362,0.002642838,0.004338222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001709544,"about_ca_system_score_gemma":0.003892088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01678998,"about_ca_topic_score_gemma":0.02886464,"domain_scores_codex":[0.9979583,0.0004082713,0.0002135417,0.0006672017,0.0005525255,0.0002002208],"domain_scores_gemma":[0.9977059,0.0007793725,0.0001638048,0.0003917644,0.0006778823,0.0002812925],"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":[0.002043123,0.0007602525,0.01849715,0.001597981,0.001335293,0.00117499,0.0004501697,0.1423649,0.01154241,0.003478101,0.3148731,0.5018826],"study_design_scores_gemma":[0.0006578913,0.001239367,0.009901067,0.0004106064,0.0004450382,0.00228033,0.0003833412,0.8615366,0.02844515,0.01275848,0.08170956,0.0002326135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3482985,0.01624531,0.433237,0.01367338,0.004840899,0.003821425,0.0839067,0.06488752,0.0310892],"genre_scores_gemma":[0.4783437,0.003573616,0.2801065,0.004102997,0.001050504,0.002026936,0.1978065,0.005060822,0.02792842],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01678998,"threshold_uncertainty_score":0.0333845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03604308001600156,"score_gpt":0.3684660197513305,"score_spread":0.332422939735329,"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."}}