{"id":"W2752792052","doi":"10.1016/j.ejmp.2017.07.024","title":"A review of GPU-based medical image reconstruction","year":2017,"lang":"en","type":"review","venue":"Physica Medica","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":89,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Iterative reconstruction; Workflow; Massively parallel; Graphics; Process (computing); Task (project management); Computer graphics (images); Image processing; Computer vision; Artificial intelligence; General-purpose computing on graphics processing units; Perspective (graphical); Image (mathematics); Computational science; Parallel computing","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001007422,0.0004249072,0.003366857,0.000152066,0.00009797028,0.00001200223,0.0007523575,0.0003849344,0.001678489],"category_scores_gemma":[0.003098672,0.0002993978,0.001086033,0.0002892448,0.001027362,0.00005421911,0.0001329771,0.001138323,0.0001586877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008502493,"about_ca_system_score_gemma":0.003350509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002011245,"about_ca_topic_score_gemma":3.783134e-7,"domain_scores_codex":[0.9965726,0.000146935,0.001221488,0.0005598933,0.001176493,0.0003225738],"domain_scores_gemma":[0.9957704,0.0003006717,0.001225362,0.001816445,0.0002333085,0.0006537963],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001599684,0.0001375581,1.486858e-7,0.1859115,0.00007638565,0.00001709042,0.000001437452,8.274454e-11,0.000002076704,0.0001234557,0.1173989,0.6963298],"study_design_scores_gemma":[0.0001739298,0.00004373122,2.329942e-7,0.3862904,0.001394598,0.0001696881,4.757885e-7,0.00003857807,0.000007238367,0.00006122001,0.6116812,0.0001386991],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[9.223542e-8,0.9780083,0.0007941257,0.01118394,0.0001738046,0.00149817,0.00005191001,0.0001786009,0.008111001],"genre_scores_gemma":[9.664226e-7,0.9854831,0.01084199,0.001579756,0.0007770456,0.0006211908,0.0004252965,0.00006939341,0.0002012834],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.6961911,"threshold_uncertainty_score":0.9999458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09959157461629603,"score_gpt":0.4551497504535303,"score_spread":0.3555581758372343,"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."}}