{"id":"W2977457995","doi":"10.1016/j.media.2019.101568","title":"Segmentation and quantification of infarction without contrast agents via spatiotemporal generative adversarial learning","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":71,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Western University","keywords":"Artificial intelligence; Computer science; Segmentation; Pattern recognition (psychology); Discriminator; Encoder; Generator (circuit theory); Centroid; Contrast (vision); Feature (linguistics); Power (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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007782631,0.0001226811,0.0004609612,0.0002940273,0.00006726745,0.00002513664,0.00005767926,0.0001021111,0.001211719],"category_scores_gemma":[0.0006915632,0.0001038267,0.0001330956,0.0004750632,0.0001668458,0.0001466189,0.00003087623,0.0003727484,0.00002065704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003368815,"about_ca_system_score_gemma":0.00006456335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005269399,"about_ca_topic_score_gemma":0.00001504644,"domain_scores_codex":[0.9982617,0.0001751853,0.0004278276,0.0002990069,0.0006830102,0.0001532906],"domain_scores_gemma":[0.9991493,0.00008412681,0.0002502966,0.0001560646,0.0001540122,0.0002061686],"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":[0.0001720409,0.0001377869,0.8294321,0.000112043,0.00175379,0.00001111714,0.0007221319,0.0008583618,0.1092206,0.00004863456,0.0001100683,0.05742126],"study_design_scores_gemma":[0.002047946,0.0001495543,0.1663512,0.00005054551,0.00181814,0.00001255252,0.0002454051,0.8250545,0.003670983,0.00002074081,0.0004668469,0.0001115711],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6496129,0.00005924918,0.348339,0.001415586,0.0000913229,0.0001855465,0.000001607543,0.00002498215,0.0002698104],"genre_scores_gemma":[0.9937786,0.00009070695,0.00482224,0.0003621098,0.0001227802,0.000006635542,0.0002941349,0.00001345083,0.000509333],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8241961,"threshold_uncertainty_score":0.9997013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008969040013805935,"score_gpt":0.3076035449077018,"score_spread":0.2986345048938959,"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."}}