{"id":"W4388947967","doi":"10.1016/j.compmedimag.2023.102315","title":"Image reconstruction using UNET-transformer network for fast and low-dose PET scans","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal","funders":"Alliance de recherche numérique du Canada; Institut de Valorisation des Données; Canada First Research Excellence Fund","keywords":"Artificial intelligence; Computer science; Mean squared error; Image quality; Ground truth; Iterative reconstruction; Residual; Imaging phantom; Maximum a posteriori estimation; Pattern recognition (psychology); Computer vision; Mathematics; Nuclear medicine; Algorithm; Image (mathematics); Statistics; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003545725,0.0004076598,0.0002527474,0.0005297657,0.0002067696,0.000650985,0.0004517107,0.00042364,0.005873129],"category_scores_gemma":[0.001034699,0.0003077739,0.0002920503,0.0005728616,0.0001496131,0.0006663199,0.0004340089,0.0004110446,0.001093084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002795068,"about_ca_system_score_gemma":0.0006619037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001961997,"about_ca_topic_score_gemma":0.003373672,"domain_scores_codex":[0.9998879,0.00002511277,0.000006744265,0.00001988464,0.0000453751,0.00001480742],"domain_scores_gemma":[0.999805,0.0000595023,0.00001589394,0.00004029504,0.00006690055,0.00001243923],"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":[0.001522281,0.0001372719,0.006788144,0.0004162119,0.0001350983,0.001039481,0.0002348668,0.09077209,0.2498336,0.01152188,0.006863711,0.6307354],"study_design_scores_gemma":[0.00005467601,0.0001712641,0.002938636,0.00003653183,0.00007865256,0.002408133,0.00008723257,0.803091,0.1765363,0.004405341,0.01014763,0.00004464455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03936034,0.0002090208,0.9549595,0.0001370515,0.00003005967,0.00005890823,0.0002760588,0.001445233,0.003523712],"genre_scores_gemma":[0.3522238,0.0003546191,0.641222,0.00010899,0.00002021481,0.00008277919,0.0006884554,0.0004993541,0.004799762],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005873129,"threshold_uncertainty_score":0.01964754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0210033796698915,"score_gpt":0.3161367965816873,"score_spread":0.2951334169117957,"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."}}