{"id":"W3153842381","doi":"10.1088/1361-6560/abfa36","title":"Improved low-dose positron emission tomography image reconstruction using deep learned prior","year":2021,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Government of Newfoundland and Labrador","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Maximum a posteriori estimation; Iterative reconstruction; Noise (video); Positron emission tomography; Image quality; Computer vision; Medical imaging; Contrast (vision); Reconstruction algorithm; Pattern recognition (psychology); Image processing; Statistical noise; Inverse problem; Image (mathematics); Nuclear medicine; Mathematics; Maximum likelihood; Machine learning; Statistics","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":[0.0001805203,0.0001133195,0.0003088965,0.000072052,0.00006220374,0.000004864542,0.00004275695,0.0001005936,0.00005290964],"category_scores_gemma":[0.000142516,0.00008423654,0.00004228649,0.0003145816,0.0003121281,0.00003879267,0.00005020667,0.0002907405,7.239314e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002487895,"about_ca_system_score_gemma":0.00005509201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007031963,"about_ca_topic_score_gemma":0.000002659364,"domain_scores_codex":[0.9991657,0.00005276993,0.0002431391,0.0002987545,0.00005416238,0.0001854364],"domain_scores_gemma":[0.999448,0.00006599995,0.00007341197,0.0002031485,0.00009611477,0.0001133124],"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":[0.00003267974,0.00007766198,0.00393629,0.00006062589,0.00001297695,0.000007856291,0.00007115959,8.868601e-8,0.87191,0.0004624926,0.0001273029,0.1233008],"study_design_scores_gemma":[0.01570867,0.0021451,0.01392826,0.003910225,0.0008535508,0.001891765,0.002304097,0.1543916,0.6805414,0.1154003,0.007752091,0.001172889],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9591031,0.0006686994,0.03005438,0.009002,0.0001256803,0.0002724759,0.000002273167,0.00006928811,0.0007021165],"genre_scores_gemma":[0.938587,0.001153931,0.05805914,0.001404454,0.0005978806,0.00002363101,0.0001027985,0.00001687548,0.00005433205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1913687,"threshold_uncertainty_score":0.3435066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1058321050274913,"score_gpt":0.4070491510941627,"score_spread":0.3012170460666714,"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."}}