{"id":"W2724559516","doi":"10.1038/sdata.2017.77","title":"Matched computed tomography segmentation and demographic data for oropharyngeal cancer radiomics challenges","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"Columbia College","funders":"Division of Mathematical Sciences; National Cancer Institute; National Science Foundation; National Institutes of Health; Andrew Sabin Family Foundation; National Institute of Dental and Craniofacial Research; University of Texas MD Anderson Cancer Center; Radiological Society of North America; Varian Medical Systems","keywords":"Radiomics; Head and neck cancer; Medicine; Data extraction; Workflow; Segmentation; Leverage (statistics); Radiation therapy; Medical physics; Computer science; Artificial intelligence; Radiology; MEDLINE; Database; Biology","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":[0.001768177,0.0004086979,0.0004731211,0.002466273,0.0004482675,0.00115924,0.0008776573,0.001077703,0.002351241],"category_scores_gemma":[0.009565775,0.0002329876,0.0006039433,0.002367188,0.0004828539,0.0007477282,0.001340511,0.0006054917,0.001663856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001310825,"about_ca_system_score_gemma":0.002102591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01096901,"about_ca_topic_score_gemma":0.01499119,"domain_scores_codex":[0.998641,0.0002440968,0.0001563178,0.0004197762,0.000423214,0.000115642],"domain_scores_gemma":[0.9961442,0.0009436246,0.0006438475,0.001182031,0.0008140143,0.0002722871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001620113,0.000555628,0.4733896,0.000971965,0.0003147386,0.002078069,0.001115513,0.0420476,0.02159411,0.0149218,0.16245,0.2789409],"study_design_scores_gemma":[0.0001430585,0.0004078919,0.3891453,0.0003732247,0.0002058283,0.004659818,0.002164212,0.2388697,0.05116423,0.02505111,0.2876309,0.0001846833],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.5870688,0.00231444,0.09528624,0.00810946,0.0006770449,0.0009300499,0.2819577,0.00896666,0.01468962],"genre_scores_gemma":[0.6811271,0.0007427536,0.06587657,0.0005916591,0.0002387234,0.0004784023,0.2478548,0.0004952949,0.002594711],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01096901,"threshold_uncertainty_score":0.02181035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09448940482926785,"score_gpt":0.3767482580760038,"score_spread":0.2822588532467359,"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."}}