{"id":"W4391428764","doi":"10.1016/j.zemedi.2024.01.002","title":"Enhanced direct joint attenuation and scatter correction of whole-body PET images via context-aware deep networks","year":2024,"lang":"de","type":"article","venue":"Zeitschrift für Medizinische Physik","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Canadian Institutes of Health Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Nvidia; National Science Foundation","keywords":"Correction for attenuation; Artificial intelligence; Attenuation; Computer science; Context (archaeology); Convolutional neural network; Deep learning; Positron emission tomography; Inference; Convolution (computer science); Pattern recognition (psychology); Spurious relationship; Computer vision; Artificial neural network; Machine learning; Physics; Nuclear medicine; Optics; Geology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008741159,0.0006155006,0.001077872,0.0002776086,0.000212121,0.0001505553,0.0002456431,0.000292943,0.0003409175],"category_scores_gemma":[0.000277659,0.0005319523,0.0003222028,0.00070138,0.0006858635,0.0003532011,0.0002129056,0.001240088,0.00034348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002515586,"about_ca_system_score_gemma":0.0001739072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001607974,"about_ca_topic_score_gemma":0.000008102988,"domain_scores_codex":[0.9962425,0.0002327384,0.001071442,0.001049468,0.0007433121,0.0006605528],"domain_scores_gemma":[0.997421,0.0005416197,0.0003745642,0.0007803481,0.0004010561,0.0004814262],"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":[0.0001992446,0.0008189328,0.0002783768,0.002346617,0.001394033,0.0001331188,0.001976511,0.00006510496,0.5774357,0.001624266,0.156381,0.2573471],"study_design_scores_gemma":[0.002004464,0.0008323114,0.002488688,0.007321157,0.003216732,0.00008936949,0.0007494625,0.3667148,0.4166879,0.0001294231,0.1986695,0.001096219],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04477081,0.08206688,0.7838596,0.05667568,0.01316177,0.005424683,0.0002833699,0.00221981,0.01153743],"genre_scores_gemma":[0.9884141,0.004193096,0.0008263034,0.00143217,0.003017047,0.0003166368,0.0006108501,0.0001363053,0.001053508],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9436433,"threshold_uncertainty_score":0.9997132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01335547862609124,"score_gpt":0.3010386811735077,"score_spread":0.2876832025474165,"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."}}