{"id":"W2055642961","doi":"10.1088/1742-6596/489/1/012009","title":"Automated segmentation and dose-volume analysis with DICOMautomaton","year":2014,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"BC Cancer Agency; Varian Medical Systems; Conquer Cancer Foundation","keywords":"Segmentation; Volume (thermodynamics); Computation; Computer science; Sensitivity (control systems); Exploratory analysis; Artificial intelligence; Computer vision; Image segmentation; Data mining; Pattern recognition (psychology); Algorithm; Engineering; Data science","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":[],"consensus_categories":[],"category_scores_codex":[0.00009942584,0.0001358263,0.0003238176,0.00008253702,0.00007334406,0.00009136309,0.000100324,0.00002000508,0.00006371405],"category_scores_gemma":[0.000002060786,0.000102886,0.00007213237,0.0002576541,0.0001045634,0.0006821037,0.00001449103,0.0001163951,4.989182e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001549388,"about_ca_system_score_gemma":0.00004577689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001695439,"about_ca_topic_score_gemma":0.000002056863,"domain_scores_codex":[0.9993138,0.00005007283,0.0002359979,0.0001060242,0.0001733386,0.0001208004],"domain_scores_gemma":[0.9991421,0.00002643581,0.0004352156,0.0001212112,0.0002147969,0.00006027701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002336578,0.0002371977,0.352782,0.0000434087,0.002735491,0.000004723129,0.002321604,0.002404504,0.04976579,0.1073295,0.0002392254,0.4819029],"study_design_scores_gemma":[0.003440801,0.002916169,0.1413298,0.0002610319,0.002105178,0.00004586513,0.002193,0.08374482,0.6935477,0.06591506,0.003213644,0.001286939],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2485149,0.00001479932,0.7508602,0.00008823493,0.00001966376,0.00005400719,0.000005310418,0.00006650684,0.0003764144],"genre_scores_gemma":[0.9591447,0.00001400516,0.0406193,0.00001878339,0.0001126622,0.000003722844,0.000008127538,0.00001244788,0.00006627363],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7106298,"threshold_uncertainty_score":0.4195568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007137373619028204,"score_gpt":0.2579056321772521,"score_spread":0.2507682585582239,"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."}}