{"id":"W3114149408","doi":"10.1002/mp.14665","title":"Three‐dimensional MRI‐based treatment planning approach for non‐invasive ocular proton therapy","year":2020,"lang":"en","type":"article","venue":"Medical Physics","topic":"Ocular Oncology and Treatments","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Medizinische Universität Wien; Paul Scherrer Institut; Stichting voor de Technische Wetenschappen; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Universität Wien; Varian Medical Systems","keywords":"Sclera; Proton therapy; Margin (machine learning); Medical imaging; Magnetic resonance imaging; Nuclear medicine; Radiation treatment planning; Optic nerve; Segmentation; Artificial intelligence; Computer science; Medicine; Radiation therapy; Ophthalmology; Radiology","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":[0.0000865484,0.0002240189,0.0004314564,0.00001677071,0.0001147853,0.000005987823,0.0000807203,0.0001834212,0.00006907275],"category_scores_gemma":[0.00007571459,0.0001518528,0.0002302664,0.0001134906,0.0001202774,0.00003207365,0.0000188707,0.0001763489,0.00002858304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008467434,"about_ca_system_score_gemma":0.0005405868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000856877,"about_ca_topic_score_gemma":5.401387e-7,"domain_scores_codex":[0.9986793,0.00002490536,0.0001858717,0.0003818879,0.000454806,0.0002732727],"domain_scores_gemma":[0.9991574,0.0001433786,0.00006420149,0.0001895625,0.00006144089,0.0003840134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.02193356,0.03742606,0.6164978,0.002477993,0.0103781,0.005206289,0.004794084,0.002617365,0.006095345,0.0007036831,0.0199584,0.2719113],"study_design_scores_gemma":[0.1419833,0.04185488,0.01700514,0.0007839574,0.002035804,0.0000978406,0.0001315802,0.323185,0.434161,0.003757125,0.03345597,0.001548354],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5234388,0.00102521,0.445969,0.01673683,0.0002565118,0.01058045,0.000061733,0.0002814898,0.00165006],"genre_scores_gemma":[0.9806409,0.00001818773,0.008516834,0.007838387,0.0009829442,0.001200953,0.0007132134,0.00005011675,0.00003849205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5994927,"threshold_uncertainty_score":0.6192378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05947109829240313,"score_gpt":0.3246093696619788,"score_spread":0.2651382713695757,"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."}}