{"id":"W2178972469","doi":"10.1109/23.940180","title":"Cross-validation stopping rule for ML-EM reconstruction of dynamic PET series: effect on image quality and quantitative accuracy","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Nuclear Science","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Image quality; Iterative reconstruction; Expectation–maximization algorithm; Smoothing; Imaging phantom; Projection (relational algebra); Positron emission tomography; Algorithm; Image resolution; Computer science; Computation; Artificial intelligence; Maximization; Image (mathematics); Mathematics; Computer vision; Statistics; Nuclear medicine; Maximum likelihood; Mathematical optimization; Physics; Optics","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":[0.0007657242,0.0001025647,0.0001848889,0.0001660665,0.0003834504,0.00006031311,0.0001052361,0.00003574145,0.00007354149],"category_scores_gemma":[0.0002129586,0.00009024494,0.00006401181,0.0004130714,0.0007202157,0.0004224628,0.000001980977,0.0001660377,0.000009597199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008631533,"about_ca_system_score_gemma":0.00005710211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003096865,"about_ca_topic_score_gemma":0.000003318348,"domain_scores_codex":[0.9989437,0.00003696876,0.000258686,0.0003322474,0.0002619748,0.000166411],"domain_scores_gemma":[0.9990491,0.0002665678,0.0001233024,0.0002706493,0.0001844645,0.0001058842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008383571,0.0002877205,0.00009750355,0.0002245818,0.00002142975,0.000002691495,0.0005386111,0.000139436,0.8426004,0.001054949,0.00003934088,0.154155],"study_design_scores_gemma":[0.005871498,0.008977788,0.03130153,0.001671943,0.0003128614,0.001053783,0.002403894,0.3030474,0.640578,0.002033755,0.001766967,0.0009806663],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8866264,0.000002265993,0.1112949,0.001143087,0.0001074665,0.0005204433,0.0000289829,0.0001047901,0.0001716449],"genre_scores_gemma":[0.9465826,0.00005573894,0.05307616,0.0001126733,0.000008764418,0.0000438927,0.000001270352,0.00001261469,0.0001062431],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3029079,"threshold_uncertainty_score":0.3680082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03819305237764763,"score_gpt":0.4022246556067163,"score_spread":0.3640316032290687,"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."}}