{"id":"W2516447258","doi":"10.1118/1.4961806","title":"Poster ‐ 32: Atlas Selection for Automated Segmentation of Pelvic CT for Prostate Radiotherapy","year":2016,"lang":"en","type":"article","venue":"Medical Physics","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Juravinski Cancer Centre","funders":"","keywords":"Atlas (anatomy); Segmentation; Computer science; Artificial intelligence; Sørensen–Dice coefficient; Image registration; Pattern recognition (psychology); Computer vision; Medical imaging; Image segmentation; Nuclear medicine; Medicine; Image (mathematics); Anatomy","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":[0.0001513665,0.00008632032,0.0001700502,0.00002723412,0.00002579559,0.000006997499,0.00006135082,0.00003160446,0.00005160697],"category_scores_gemma":[0.00008348022,0.00005765722,0.00008751491,0.0001160366,0.00004326651,0.00006915481,0.000003749764,0.00004194511,0.000004238418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004299032,"about_ca_system_score_gemma":0.00002598061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006147133,"about_ca_topic_score_gemma":0.000001362573,"domain_scores_codex":[0.9992939,0.00001240317,0.0001950112,0.000108919,0.0002254163,0.0001643069],"domain_scores_gemma":[0.9995912,0.0001590496,0.00003717302,0.00006804433,0.00005637239,0.00008810867],"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":[0.00003869929,0.0001236948,0.002784697,0.0006033927,0.0003734289,9.38004e-7,0.0003316611,0.0005313409,0.1420248,0.00007611999,0.03197835,0.8211328],"study_design_scores_gemma":[0.002941555,0.0001387667,0.0002616173,0.0002120151,0.00009714196,0.00000293226,0.00001090857,0.725577,0.2646806,0.001153673,0.004717049,0.0002067451],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1251465,0.00006855555,0.8730456,0.0008083123,0.0002011521,0.0002914582,0.00002806083,0.0003597533,0.00005060303],"genre_scores_gemma":[0.9972758,0.00006270505,0.001787741,0.0001356725,0.0003307693,0.0000883079,0.00004753325,0.000032361,0.0002391],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8721293,"threshold_uncertainty_score":0.2351193,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008264828903773244,"score_gpt":0.2658890906252284,"score_spread":0.2576242617214552,"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."}}