{"id":"W2949076424","doi":"10.1007/s00330-019-06229-1","title":"Direct attenuation correction of brain PET images using only emission data via a deep convolutional encoder-decoder (Deep-DAC)","year":2019,"lang":"en","type":"article","venue":"European Radiology","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":108,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Tehran University of Medical Sciences and Health Services","keywords":"Artificial intelligence; Attenuation; Image quality; Computer science; Convolutional neural network; Encoder; Pattern recognition (psychology); Correction for attenuation; Nuclear medicine; Pixel; Computer vision; Positron emission tomography; Medicine; Physics; Image (mathematics); Optics","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":[0.0007793138,0.0001344469,0.0003032473,0.0001033814,0.00006463547,0.000006700573,0.0002359208,0.00004777125,0.0003878472],"category_scores_gemma":[0.0004464336,0.0001160271,0.00005534412,0.0001462134,0.0001633056,0.00009139178,0.0001593684,0.0002015051,0.00007480532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005694462,"about_ca_system_score_gemma":0.0000858916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005456982,"about_ca_topic_score_gemma":0.000004205245,"domain_scores_codex":[0.9985269,0.00031815,0.0003678535,0.0004227106,0.0001682844,0.0001961231],"domain_scores_gemma":[0.9986777,0.0002181018,0.0001981878,0.0006897406,0.0001087941,0.0001074994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001445174,0.0003194203,0.04984156,0.0001178652,0.00009245145,0.00006491922,0.0002052543,0.0001503266,0.796721,0.0002711983,0.1230721,0.02899938],"study_design_scores_gemma":[0.002270907,0.0004569554,0.08435384,0.0003427459,0.0002401017,0.003721162,0.00009789134,0.7840395,0.007256103,0.0001674243,0.1166085,0.000444872],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6165797,0.0002330743,0.3657063,0.003724878,0.0005847183,0.0006594318,0.00004151655,0.0002384284,0.01223199],"genre_scores_gemma":[0.9724542,0.00004352003,0.02403879,0.0008410554,0.0002941069,0.000003786448,0.0008269935,0.00003209574,0.001465376],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.789465,"threshold_uncertainty_score":0.4731449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03679750417127457,"score_gpt":0.3243212062934852,"score_spread":0.2875237021222106,"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."}}