{"id":"W4400184938","doi":"10.1186/s40658-024-00660-0","title":"Kinetic model-informed deep learning for multiplexed PET image separation","year":2024,"lang":"en","type":"article","venue":"EJNMMI Physics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; King's College London; Centre For Medical Engineering, King’s College London; Wellcome Trust; McGill University","keywords":"Computer science; Artificial intelligence; Algorithm; Positron emission tomography; Deep learning; Parameterized complexity; Artificial neural network; Nuclear medicine; Medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008636329,0.0001092275,0.0001487661,0.00003199854,0.00007667863,0.00004823659,0.00005964835,0.00003260469,0.00002879228],"category_scores_gemma":[0.00009400366,0.00009461057,0.0001040058,0.0001543389,0.000050158,0.0001106911,0.00002267644,0.0002134471,0.00007076817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004900828,"about_ca_system_score_gemma":0.00007952505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005456678,"about_ca_topic_score_gemma":9.381843e-7,"domain_scores_codex":[0.9992859,0.000006522651,0.0001726107,0.0001975233,0.0001559832,0.0001814527],"domain_scores_gemma":[0.999516,0.0001001488,0.00003117258,0.0001808081,0.00007863073,0.00009325997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001163267,0.0003604633,0.00009939379,0.001840894,0.0001444947,0.00002921542,0.002004027,0.004728338,0.6478214,0.08360272,0.1237658,0.135487],"study_design_scores_gemma":[0.0003094059,0.00006702203,0.00002704913,0.00009927928,0.00007475814,0.000009356436,0.00002401262,0.9436073,0.009878066,0.005864174,0.03993997,0.00009965748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01582964,0.00005479486,0.9763364,0.002560562,0.00006288435,0.0007431449,0.000008568564,0.0006703198,0.003733668],"genre_scores_gemma":[0.7963882,0.00004276607,0.1999422,0.0003333033,0.0003580739,0.0002940348,0.0002935357,0.00003521043,0.002312665],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9388789,"threshold_uncertainty_score":0.3858107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02959621409008822,"score_gpt":0.3728947973629704,"score_spread":0.3432985832728822,"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."}}