{"id":"W4386536838","doi":"10.2139/ssrn.4562884","title":"Deep-Learning-Based Automated Quantification of Ventilation Defects on 3d Isotropic Hyperpolarized 129xe Lung MRI","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Atomic and Subatomic Physics Research","field":"Physics and Astronomy","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lawson Health Research Institute; Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre; Western University","funders":"","keywords":"Lung ventilation; Isotropy; Magnetic resonance imaging; Lung; Ventilation (architecture); Medicine; Nuclear magnetic resonance; Radiology; Biomedical engineering; Physics; Engineering; Internal medicine; Optics; Mechanical engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005231625,0.0006205979,0.000523166,0.0008292854,0.0001448193,0.000814556,0.0006342309,0.0008869121,0.001108358],"category_scores_gemma":[0.001243636,0.000374501,0.0004138415,0.0004742006,0.0002286296,0.0005559961,0.0007733912,0.0006256242,0.0005662371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002833796,"about_ca_system_score_gemma":0.0006431267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002675432,"about_ca_topic_score_gemma":0.004275429,"domain_scores_codex":[0.9998593,0.00002938204,0.000007910996,0.00003524265,0.00003966385,0.00002851186],"domain_scores_gemma":[0.9996709,0.0001403588,0.00005523012,0.00003446003,0.00007537488,0.00002379799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006070161,0.0002389216,0.009881451,0.0003847434,0.000180133,0.0003131578,0.0001210197,0.2214453,0.1624283,0.002906556,0.00436802,0.5971254],"study_design_scores_gemma":[0.00000919286,0.00004136568,0.002163995,0.00002066262,0.00002036817,0.0001621906,0.00001677868,0.9719654,0.02339771,0.001523303,0.0006653595,0.00001358514],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1913119,0.001261229,0.8009064,0.0003772777,0.00004384567,0.00008879609,0.0008994614,0.003194078,0.001917055],"genre_scores_gemma":[0.785349,0.0007202448,0.2092896,0.0001632767,0.00005087498,0.00007315929,0.001243571,0.0002461729,0.002864202],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002675432,"threshold_uncertainty_score":0.005319655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01696229912410951,"score_gpt":0.2988355034103883,"score_spread":0.2818732042862788,"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."}}