{"id":"W4318939205","doi":"10.1016/j.neurad.2023.01.157","title":"The performance of machine learning approaches for attenuation correction of PET in neuroimaging: A meta-analysis","year":2023,"lang":"en","type":"review","venue":"Journal of Neuroradiology","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Montreal Neurological Institute and Hospital; Lawson Health Research Institute; Western University","funders":"Canada First Research Excellence Fund; Academic Medical Organization of Southwestern Ontario; London Health Sciences Centre","keywords":"Neuroimaging; Meta-analysis; Correction for attenuation; Computer science; Artificial intelligence; Attenuation; Positron emission tomography; Machine learning; Psychology; Neuroscience; Medicine; Physics; Optics; Pathology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00158832,0.0001574165,0.002579561,0.0005982439,0.0000421314,0.000004908467,0.0002161978,0.00007312623,0.000005665553],"category_scores_gemma":[0.0009849982,0.0000878197,0.001462805,0.0008655468,0.0001261907,0.00002938892,0.00003260068,0.0007646751,4.796934e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002874808,"about_ca_system_score_gemma":0.0001339549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008275258,"about_ca_topic_score_gemma":0.000002604733,"domain_scores_codex":[0.9978107,0.0003500108,0.001350519,0.0001633927,0.0001901026,0.000135269],"domain_scores_gemma":[0.9960706,0.001402248,0.002071622,0.0002364034,0.0001729891,0.00004612125],"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":[0.0004338044,0.0006801463,0.002943719,0.02667912,0.08702851,0.00009757319,0.0002219093,0.004448975,0.0001906477,0.0004113208,0.005247544,0.8716167],"study_design_scores_gemma":[0.0004856527,0.00154138,0.0004461999,0.0008461276,0.2688051,0.001804475,0.00002613258,0.1539075,0.00001810775,0.00005049138,0.5718938,0.0001751442],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002002963,0.9903824,0.003374032,0.002684297,0.0002740205,0.001195393,0.0000208409,0.00002645175,0.00003964156],"genre_scores_gemma":[0.005688231,0.9928168,0.001013369,0.00003008603,0.00008182969,0.0000801039,0.00003931226,0.0000285428,0.0002216951],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8714416,"threshold_uncertainty_score":0.3581184,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3020113681382617,"score_gpt":0.4142663082121316,"score_spread":0.1122549400738699,"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."}}