{"id":"W4414603395","doi":"10.1109/jbhi.2025.3615075","title":"Low-Count PET Image Reconstruction With Generalized Sparsity Priors via Unrolled Deep Networks","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperparameter; Prior probability; Deep learning; Iterative reconstruction; Pattern recognition (psychology); Regularization (linguistics); Expectation–maximization algorithm; Thresholding; Medical imaging; Iterative method","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":[0.001029697,0.0001227619,0.000493296,0.0002213593,0.0001534325,0.00002687332,0.00009499718,0.00008438004,0.00003538376],"category_scores_gemma":[0.00003890119,0.0000775833,0.00006469835,0.0003209849,0.0003150802,0.0001292934,0.00002378872,0.0005326286,0.000001578384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001116758,"about_ca_system_score_gemma":0.0004806506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002374558,"about_ca_topic_score_gemma":0.000004050647,"domain_scores_codex":[0.9981334,0.00002662632,0.001161546,0.00006627384,0.0003654242,0.0002467036],"domain_scores_gemma":[0.9984503,0.00004640998,0.0006251293,0.000142403,0.0002242821,0.0005114878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001672941,0.001282821,0.006116529,0.005379605,0.0006237324,0.000165763,0.001843176,0.00006096999,0.001283715,0.001204178,0.1551956,0.825171],"study_design_scores_gemma":[0.02183353,0.004362014,0.0115824,0.00790963,0.0007133512,0.01552077,0.001373917,0.8373139,0.0009604307,0.002829443,0.0949562,0.0006444002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2214678,0.0001428847,0.7501073,0.0273411,0.0003119602,0.0003740584,0.000003028592,0.00003941731,0.0002124123],"genre_scores_gemma":[0.2746307,0.005307189,0.7022426,0.01692493,0.0006878432,0.0000161067,0.00002635395,0.00001748963,0.0001467756],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.837253,"threshold_uncertainty_score":0.3163755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01420148236588148,"score_gpt":0.3134964501509505,"score_spread":0.299294967785069,"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."}}