{"id":"W4367045625","doi":"10.4274/dir.2023.232113","title":"LAVA HyperSense and deep-learning reconstruction for near-isotropic (3D) enhanced magnetic resonance enterography in patients with Crohn’s disease: utility in noise reduction and image quality improvement","year":2023,"lang":"en","type":"article","venue":"Diagnostic and Interventional Radiology","topic":"Inflammatory Bowel Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"CARE Canada","funders":"Inje University","keywords":"Medicine; Image quality; Artificial intelligence; Coronal plane; Iterative reconstruction; Contrast-to-noise ratio; Computer vision; Magnetic resonance imaging; Contrast (vision); Nuclear medicine; Radiology; Computer science; Image (mathematics)","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":[0.0002056405,0.0001254541,0.0001429388,0.00008075407,0.00007073309,0.0000199992,0.00003346782,0.00007110323,0.00001077856],"category_scores_gemma":[0.0004075883,0.0001246155,0.0000448466,0.00006437198,0.000290865,0.00001682137,0.00005132134,0.00007948639,6.161758e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001646909,"about_ca_system_score_gemma":0.00002002791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001916045,"about_ca_topic_score_gemma":0.00009547196,"domain_scores_codex":[0.9989159,0.0001515115,0.0002708213,0.0004076134,0.00005920269,0.0001949298],"domain_scores_gemma":[0.999603,0.00007737486,0.00007870014,0.00009841436,0.00006500935,0.00007754606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001857866,0.0001214193,0.9361457,0.0001450757,0.00001770335,0.00001432522,0.00006268779,0.00001321391,0.00129148,0.00007394143,0.00002125281,0.0602353],"study_design_scores_gemma":[0.002465002,0.0005639271,0.9958432,0.00007679668,0.00001682739,0.000004683638,0.00009807712,0.0003917585,0.00006308036,0.0002418771,0.0001102089,0.0001245372],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9980836,0.0009937768,0.0002224724,0.00003564985,0.00009912505,0.0004846875,0.00006151557,0.00000979209,0.000009385087],"genre_scores_gemma":[0.9986568,0.0004603473,0.000285445,0.00002334136,0.00003109282,0.0001896316,0.0003175668,0.00001013223,0.00002564119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06011077,"threshold_uncertainty_score":0.5081671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005008434341036368,"score_gpt":0.2360916246415912,"score_spread":0.2310831903005549,"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."}}