{"id":"W3034964388","doi":"10.1109/jstsp.2020.3001525","title":"Enhanced Deep-Learning-Based Magnetic Resonance Image Reconstruction by Leveraging Prior Subject-Specific Brain Imaging: Proof-of-Concept Using a Cohort of Presumed Normal Subjects","year":2020,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"General Electric (Canada); Foothills Medical Centre; University of Calgary; Alberta Health Services","funders":"Science and Engineering Research Council","keywords":"Artificial intelligence; Computer science; Iterative reconstruction; Wilcoxon signed-rank test; Magnetic resonance imaging; Neuroimaging; Image quality; Pattern recognition (psychology); Deep learning; Computer vision; Similarity (geometry); Mean squared error; Nuclear medicine; Mathematics; Image (mathematics); Medicine; Statistics; Radiology","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":[0.0002962788,0.0002047492,0.0005546905,0.0002103657,0.00009459293,0.00002753499,0.0001700938,0.0001000151,0.00003474254],"category_scores_gemma":[0.0001976871,0.0002050109,0.00009231718,0.00101114,0.0001931896,0.0003267026,0.00001680433,0.0007748455,1.069751e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001527261,"about_ca_system_score_gemma":0.0004882554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000851388,"about_ca_topic_score_gemma":0.000001449818,"domain_scores_codex":[0.9978892,0.00009598128,0.001030968,0.0002844191,0.0004061446,0.0002932533],"domain_scores_gemma":[0.9976783,0.0001056947,0.001024359,0.0001086817,0.0009575912,0.0001254001],"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":[0.0004713827,0.0001292055,0.004654027,0.0002379958,0.000008095407,0.0000203487,0.0007474646,0.003070045,0.7091455,0.000002194273,0.00004251345,0.2814712],"study_design_scores_gemma":[0.00180433,0.0005238328,0.0015649,0.001134716,0.00006455671,0.000161169,0.0001762315,0.06814162,0.9257721,0.00009011336,0.0003721677,0.0001942568],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4584829,0.003232059,0.5373999,0.000375551,0.00002784643,0.0003863439,0.000002654812,0.00002817043,0.00006455104],"genre_scores_gemma":[0.9138634,0.00004669336,0.08573624,0.00009559848,0.0001921613,0.000009416282,0.000005046425,0.00003339441,0.00001810626],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4553804,"threshold_uncertainty_score":0.8360104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01537599928606186,"score_gpt":0.2737049503597645,"score_spread":0.2583289510737026,"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."}}