{"id":"W2070255845","doi":"10.1118/1.3244101","title":"Sci—Wed PM: Delivery—09: Automatic Contrast Enhancement on Electronic Portal Images Based on Human Visual System Properties","year":2009,"lang":"en","type":"article","venue":"Medical Physics","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Cancer Agency; University of Victoria","funders":"","keywords":"Artificial intelligence; Computer vision; Computer science; Image-guided radiation therapy; Contrast (vision); Human visual system model; Noise (video); Image quality; Medical imaging; Imaging phantom; Fiducial marker; Image noise; Metric (unit); Image (mathematics); Medicine; Nuclear medicine","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005692583,0.0003370768,0.0003872161,0.00009282675,0.0002462426,0.0001645536,0.000994427,0.00009561087,0.0000546335],"category_scores_gemma":[0.00005679993,0.0002700691,0.0001143956,0.0002975751,0.0001385929,0.0003256426,0.00009229003,0.0004241809,0.0001341189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003455802,"about_ca_system_score_gemma":0.0003218924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001032896,"about_ca_topic_score_gemma":0.000001580763,"domain_scores_codex":[0.9963488,0.000137793,0.0004587649,0.0005937248,0.001739546,0.0007213437],"domain_scores_gemma":[0.9988541,0.0000647408,0.0001754417,0.0006069736,0.0001083522,0.0001903742],"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":[0.0001165799,0.005932316,0.00004367988,0.0005024928,0.0001397431,0.000437253,0.0005778536,0.0001189103,0.1181588,0.05976978,0.01628927,0.7979133],"study_design_scores_gemma":[0.001072022,0.00334757,0.000220174,0.001035724,0.00002287302,0.000005114156,0.00001477193,0.2895185,0.7033815,0.0007653986,0.0001216062,0.0004947078],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09917442,0.00006500777,0.8917903,0.001213891,0.0002496863,0.000843727,0.000001793289,0.001507824,0.005153386],"genre_scores_gemma":[0.9967498,0.000004774353,0.0007876658,0.001957115,0.0002605092,0.00008639052,0.0000117488,0.00001937001,0.0001226656],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8975753,"threshold_uncertainty_score":0.9999751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01247581731438002,"score_gpt":0.2709198903816555,"score_spread":0.2584440730672755,"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."}}