{"id":"W3097077265","doi":"10.1016/j.radonc.2020.10.016","title":"Non-invasive imaging prediction of tumor hypoxia: A novel developed and externally validated CT and FDG-PET-based radiomic signatures","year":2020,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"Interreg; Eurostars; Stichting voor de Technische Wetenschappen; Horizon 2020 Framework Programme; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Medicine; Radiomics; Hypoxia (environmental); Confidence interval; Tumor hypoxia; Nuclear medicine; Radiology; Radiation therapy; Internal medicine","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":[0.0003086377,0.0002000225,0.0005755664,0.000130188,0.00009017457,0.00002409865,0.00006997189,0.00004666849,0.00002915668],"category_scores_gemma":[0.0002070546,0.000169948,0.00004714758,0.0001402107,0.0003464562,0.00007236155,0.00002685746,0.0004063802,2.982499e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008583064,"about_ca_system_score_gemma":0.0002962282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005947344,"about_ca_topic_score_gemma":0.000003983439,"domain_scores_codex":[0.9988309,0.00006934543,0.0003407766,0.0003849774,0.0001443331,0.0002296749],"domain_scores_gemma":[0.9991096,0.0002844371,0.0001737331,0.000102359,0.00005642509,0.000273448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001064445,0.0001435664,0.06916185,0.0003722235,0.0002350454,0.0007397458,0.001195626,0.00009600623,0.88807,0.0000784939,0.000773077,0.03806987],"study_design_scores_gemma":[0.04068988,0.004030057,0.3112644,0.0007321064,0.0005805691,0.007673434,0.0004681125,0.5743816,0.02666202,0.0001179587,0.03271199,0.000687812],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9682621,0.003789838,0.01860159,0.008654351,0.0001287421,0.0003703156,0.00001627288,0.00005264041,0.0001241173],"genre_scores_gemma":[0.9662831,0.001169686,0.02335439,0.008878768,0.0002253701,0.00001229442,0.000018866,0.00003556308,0.0000219419],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8614081,"threshold_uncertainty_score":0.6930279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01419785153126344,"score_gpt":0.2840432906275348,"score_spread":0.2698454390962713,"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."}}