{"id":"W4200269404","doi":"10.1007/s12350-021-02875-5","title":"Deep learning-based attenuation map generation and correction; could it be useful clinically?","year":2021,"lang":"en","type":"letter","venue":"Journal of Nuclear Cardiology","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Libin Cardiovascular Institute of Alberta; University of Calgary","funders":"","keywords":"Medicine; Correction for attenuation; Attenuation; Deep learning; MEDLINE; Medical physics; Radiology; Artificial intelligence; Positron emission tomography; 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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007151323,0.0001771235,0.0007885791,0.0001606947,0.00009971838,0.00003494994,0.000102979,0.0008523386,0.0002355996],"category_scores_gemma":[0.0007748329,0.0001523659,0.000331732,0.00009139434,0.0001786585,0.00004016494,0.00003837461,0.003148143,0.00001491532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001009717,"about_ca_system_score_gemma":0.0001657682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004245455,"about_ca_topic_score_gemma":6.426262e-7,"domain_scores_codex":[0.9980887,0.0003409265,0.000765839,0.0002662866,0.0003514104,0.0001868629],"domain_scores_gemma":[0.998093,0.0002840147,0.0006588827,0.0002535415,0.0005885052,0.000122042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003667247,0.00002057678,0.0009344168,0.00005041064,0.0001544382,0.0004975597,0.00002559975,0.0001650619,0.0006361453,0.000003020752,0.9959791,0.001497022],"study_design_scores_gemma":[0.0005905578,0.0006136258,0.0006945952,0.0001481581,0.0004891797,0.002105864,0.00003631982,0.01688767,0.00001190968,0.00001359167,0.9782838,0.0001246924],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.003048973,0.0002835695,0.01811744,0.9766537,0.001281452,0.0002004475,0.000003481498,0.00004891828,0.0003619898],"genre_scores_gemma":[0.02440642,0.00135422,0.01215908,0.9439893,0.0162615,0.00001299489,0.0004165561,0.00009824515,0.001301668],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.03266441,"threshold_uncertainty_score":0.9991516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06023460611190398,"score_gpt":0.333047702868856,"score_spread":0.272813096756952,"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."}}