{"id":"W3042519501","doi":"10.1016/j.media.2020.101791","title":"Attention convolutional neural network for accurate segmentation and quantification of lesions in ischemic stroke disease","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":126,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Hunan Provincial Science and Technology Department; National Natural Science Foundation of China","keywords":"Hyperintensity; Stroke (engine); Segmentation; Convolutional neural network; Lesion; Magnetic resonance imaging; Artificial intelligence; Ischemic stroke; Medicine; Computer science; Pattern recognition (psychology); Cardiology; Radiology; Ischemia; Pathology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002642751,0.00009784024,0.0003009969,0.000129073,0.00003539425,0.00001038476,0.00006937624,0.00004937005,0.0001978701],"category_scores_gemma":[0.0004870231,0.00008907844,0.0001669528,0.0005891012,0.0001102327,0.00009954899,0.00005263773,0.0001074539,0.000003600695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003176079,"about_ca_system_score_gemma":0.00004838887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002385431,"about_ca_topic_score_gemma":0.000009845397,"domain_scores_codex":[0.9986835,0.00004154543,0.0004180927,0.0002845179,0.0004156647,0.000156742],"domain_scores_gemma":[0.9992583,0.0001119084,0.0001458171,0.0001333708,0.00009026504,0.0002602829],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001530941,0.0004834295,0.72745,0.0008596584,0.002684752,0.00008580754,0.0002657599,0.00209349,0.1575259,0.0001714216,0.07910738,0.02774151],"study_design_scores_gemma":[0.00192159,0.00006511613,0.300341,0.00005078497,0.003217104,0.000001247301,0.0002621633,0.6920954,0.001084506,0.000007844848,0.0008446763,0.0001085416],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.703766,0.0003053432,0.2810177,0.01420305,0.00002920294,0.0004386752,0.00007291366,0.00002381194,0.0001433461],"genre_scores_gemma":[0.9931065,0.00009379687,0.004596845,0.0008306022,0.0001227817,0.0000558848,0.001056655,0.000008443756,0.0001285095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6900019,"threshold_uncertainty_score":0.3632513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0293344987829249,"score_gpt":0.3163412260699489,"score_spread":0.287006727287024,"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."}}