{"id":"W4396223241","doi":"10.1007/s00330-024-10769-6","title":"Automated abdominal CT contrast phase detection using an interpretable and open-source artificial intelligence algorithm","year":2024,"lang":"en","type":"article","venue":"European Radiology","topic":"Renal cell carcinoma treatment","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institute of Biomedical Imaging and Bioengineering; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Neuroradiology; Interventional radiology; Medicine; Contrast (vision); Artificial intelligence; Radiology; Ultrasound; Algorithm; Phase contrast microscopy; Pattern recognition (psychology); Computer science; Neurology; Physics; Optics","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":[0.0005174786,0.0002018027,0.0003460846,0.0001592657,0.00010354,0.0001375861,0.0001332441,0.0000344346,0.00008643623],"category_scores_gemma":[0.00005757272,0.0001689564,0.00005229078,0.0001643857,0.0001741587,0.0001680722,0.0001113743,0.0002332686,0.0000969587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001351572,"about_ca_system_score_gemma":0.00005536123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001014396,"about_ca_topic_score_gemma":0.000005575571,"domain_scores_codex":[0.9983302,0.0004596695,0.0003429876,0.0005050387,0.00008127452,0.000280783],"domain_scores_gemma":[0.9993756,0.0001049361,0.00005491151,0.0002397676,0.00003750996,0.0001872915],"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":[0.0005213711,0.0002610906,0.0001017386,0.00004729607,0.0001760359,0.005391998,0.0005514578,0.00008736768,0.1607875,0.00007464918,0.00008095994,0.8319185],"study_design_scores_gemma":[0.0008482446,0.003040813,0.001525167,0.0001513346,0.0003125747,0.01737463,0.0002883581,0.9346333,0.03932237,0.00009032104,0.002169032,0.0002439042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8706558,0.001033396,0.1256609,0.00007457011,0.0004127967,0.0004013597,0.00001005294,0.0003892287,0.001361903],"genre_scores_gemma":[0.9948919,0.00002725319,0.00432973,0.0001592944,0.0003367343,0.000006090975,0.00003012674,0.00005985168,0.0001590379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9345459,"threshold_uncertainty_score":0.6889844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05173493165075577,"score_gpt":0.3353399726209769,"score_spread":0.2836050409702212,"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."}}