{"id":"W4252811963","doi":"10.1109/nssmic.1999.842828","title":"Cross-validation stopping rule for ML-EM reconstruction of dynamic PET series: effect on image quality and quantitative accuracy","year":2003,"lang":"en","type":"article","venue":"1999 IEEE Nuclear Science Symposium. Conference Record. 1999 Nuclear Science Symposium and Medical Imaging Conference (Cat. No.99CH37019)","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Smoothing; Iterative reconstruction; Image quality; Expectation–maximization algorithm; Computer science; Projection (relational algebra); Computation; Image (mathematics); Algorithm; Maximization; Imaging phantom; Image resolution; Series (stratigraphy); Noise (video); Artificial intelligence; Mathematics; Computer vision; Mathematical optimization; Statistics; Maximum likelihood; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05607221,0.001444116,0.001624653,0.001209805,0.000879437,0.001875823,0.001572735,0.00342215,0.0008850051],"category_scores_gemma":[0.1739091,0.0008678322,0.0008159259,0.0009315135,0.0019776,0.001284147,0.001538168,0.00213586,0.0003458215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001222313,"about_ca_system_score_gemma":0.001024419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002165345,"about_ca_topic_score_gemma":0.002106325,"domain_scores_codex":[0.9787071,0.01529548,0.001697494,0.001334787,0.002502503,0.0004627054],"domain_scores_gemma":[0.7043035,0.2618214,0.006425121,0.008280432,0.01802422,0.001145439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008773694,0.0004565719,0.04059498,0.0009759209,0.001125189,0.001009953,0.0007834428,0.5112388,0.05327544,0.007849658,0.003896483,0.3700199],"study_design_scores_gemma":[0.00007896246,0.0004942865,0.005366993,0.0001387194,0.0001194571,0.0004438965,0.00005645852,0.9582658,0.03284575,0.001400965,0.0007132477,0.00007550159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.226433,0.002638259,0.7654914,0.0006249584,0.0001968132,0.0001472516,0.0001534464,0.002813406,0.001501521],"genre_scores_gemma":[0.6372579,0.0004045617,0.3585232,0.0004669811,0.00005397382,0.0002567774,0.0006376971,0.001292384,0.001106501],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05607221,"threshold_uncertainty_score":0.2965417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0244900116005314,"score_gpt":0.3586917412342701,"score_spread":0.3342017296337387,"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."}}