{"id":"W2910002198","doi":"10.1016/j.media.2019.01.005","title":"Recurrent inference machines for reconstructing heterogeneous MRI data","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":85,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Artificial intelligence; Computer science; Inference; Overfitting; Deep learning; Iterative reconstruction; Process (computing); Imaging phantom; SIGNAL (programming language); Inverse problem; Compressed sensing; Pattern recognition (psychology); Benchmark (surveying); Machine learning; Real-time MRI; Magnetic resonance imaging; Artificial neural network; Mathematics; Radiology; Medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003138747,0.0001185486,0.0003981029,0.000133965,0.00005938703,0.0000189818,0.0003322327,0.00008061216,0.001568659],"category_scores_gemma":[0.0006367087,0.00009303955,0.0001740885,0.000506527,0.00007707978,0.00009485228,0.0001865211,0.000182268,0.0000430868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002399875,"about_ca_system_score_gemma":0.00006476363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000322374,"about_ca_topic_score_gemma":0.00003793147,"domain_scores_codex":[0.9986933,0.00001751999,0.0003310762,0.0004565397,0.000295607,0.0002059439],"domain_scores_gemma":[0.9983784,0.0002015376,0.0001071485,0.0009943801,0.0001160158,0.0002025476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001173959,0.0004120552,0.05480341,0.0002241883,0.001123659,0.00004703474,0.00007418503,0.0001183963,0.003638831,0.0008238704,0.004277519,0.9343395],"study_design_scores_gemma":[0.0009261442,0.0001845881,0.0006535813,0.0001259496,0.002557538,0.00007977137,0.00006054536,0.9558616,0.002523984,0.001772156,0.0349444,0.000309692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03261572,0.0002126154,0.9625412,0.002805629,0.00005369794,0.0004779189,0.0001148553,0.0001327302,0.001045683],"genre_scores_gemma":[0.4731055,0.0005114822,0.5217739,0.001158885,0.0003095583,0.0001432953,0.002123329,0.000034787,0.0008391822],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9557433,"threshold_uncertainty_score":0.9993441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03739816782364099,"score_gpt":0.4081645798559363,"score_spread":0.3707664120322953,"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."}}