{"id":"W3116759256","doi":"10.1002/nbm.4461","title":"xQSM: quantitative susceptibility mapping with octave convolutional and noise‐regularized neural networks","year":2020,"lang":"en","type":"article","venue":"NMR in Biomedicine","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of Alberta","funders":"Queensland Brain Institute; Australian Research Council; Natural Sciences and Engineering Research Council of Canada; University of Melbourne; Canadian Institutes of Health Research; University of Queensland; National Imaging Facility","keywords":"Artificial intelligence; Deep learning; Convolutional neural network; Computer science; Pattern recognition (psychology); Quantitative susceptibility mapping; Imaging phantom; Mean squared error; Mathematics; Physics; Magnetic resonance imaging; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001516839,0.0001540654,0.0003513035,0.00008579692,0.00005729647,0.00000566708,0.00005929833,0.00008101431,0.00005818294],"category_scores_gemma":[0.00007227164,0.0001143931,0.00002788871,0.000588151,0.0004485944,0.0000580958,0.00004512812,0.0002749436,0.000002310631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005311405,"about_ca_system_score_gemma":0.00003737195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000413242,"about_ca_topic_score_gemma":0.00001471109,"domain_scores_codex":[0.9989066,0.00002489052,0.000284831,0.0003683262,0.0001913369,0.0002240313],"domain_scores_gemma":[0.9993445,0.00009548575,0.00008305086,0.0001747476,0.00009669098,0.00020548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.009074829,0.001445834,0.5106535,0.001113566,0.0002707116,0.0006811082,0.007353249,0.003217728,0.3686934,0.04393274,0.009754843,0.04380853],"study_design_scores_gemma":[0.01257384,0.003702044,0.3315835,0.0005799936,0.0001548877,0.0002443387,0.002880611,0.6355169,0.0008147977,0.001707377,0.009650483,0.0005911611],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4009798,0.0007526117,0.5639002,0.03238145,0.00003126143,0.001232747,0.00002264001,0.0002043312,0.0004949486],"genre_scores_gemma":[0.9373914,0.00007674695,0.05989773,0.002256638,0.0001533443,0.00005039221,0.0001126251,0.00001648023,0.000044619],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6322992,"threshold_uncertainty_score":0.4664816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0382329727616546,"score_gpt":0.3110973562324727,"score_spread":0.2728643834708181,"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."}}