{"id":"W2891170921","doi":"10.1016/j.jmir.2018.08.002","title":"Efficient and Effective Personalization of PTV Margins During Radiation Therapy for Bladder Cancer","year":2018,"lang":"en","type":"article","venue":"Journal of medical imaging and radiation sciences","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"","keywords":"Nuclear medicine; Medicine; Bladder cancer; Margin (machine learning); Fraction (chemistry); Radiation therapy; Population; Cancer; Cone beam computed tomography; Radiology; Computer science; Computed tomography; Internal medicine; Chemistry; Chromatography","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":[0.0003197466,0.0002738224,0.0003322962,0.0002949954,0.0002845049,0.0005111241,0.0003349491,0.0002910671,0.0009035991],"category_scores_gemma":[0.001511395,0.0002280672,0.0003421262,0.0001812461,0.0001508578,0.0004641131,0.0005541436,0.0004343692,0.0002568955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001434035,"about_ca_system_score_gemma":0.0003432949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004423039,"about_ca_topic_score_gemma":0.0008777471,"domain_scores_codex":[0.999724,0.00007261204,0.00002064731,0.0000490481,0.0000966517,0.00003705831],"domain_scores_gemma":[0.9996263,0.000148832,0.00007703721,0.00007659912,0.00004405132,0.00002722369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002123762,0.0003366252,0.01977799,0.0003216545,0.000105992,0.0004558873,0.0006798167,0.03353841,0.3674854,0.0006793329,0.001821935,0.5726731],"study_design_scores_gemma":[0.0001523762,0.003916354,0.1881648,0.000126804,0.0005308252,0.00921345,0.0008675245,0.2556826,0.515248,0.003724916,0.02218051,0.0001919856],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7191684,0.007133591,0.2688075,0.0003032178,0.0002052698,0.0001001564,0.0001446111,0.000948318,0.003188984],"genre_scores_gemma":[0.965202,0.0005820731,0.03310008,0.00005722417,0.00007668439,0.00002593652,0.00005486698,0.000127111,0.000774092],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0009035991,"threshold_uncertainty_score":0.00302285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01378225253109536,"score_gpt":0.3467966551350948,"score_spread":0.3330144026039994,"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."}}