{"id":"W4382929847","doi":"10.1016/j.mri.2023.07.001","title":"Combining neural networks and image synthesis to enable automatic thoracic cavity segmentation of hyperpolarized 129Xe MRI without proton scans","year":2023,"lang":"en","type":"article","venue":"Magnetic Resonance Imaging","topic":"Atomic and Subatomic Physics Research","field":"Physics and Astronomy","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; National Science Foundation","keywords":"Dice; Segmentation; Computer science; Artificial intelligence; Convolutional neural network; Sørensen–Dice coefficient; Pattern recognition (psychology); Artificial neural network; Ventilation (architecture); Deep learning; Image segmentation; Mathematics; Physics","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":[0.000441001,0.0006263711,0.000346545,0.0004721891,0.0002032848,0.0007237335,0.0004680413,0.0006999389,0.001617183],"category_scores_gemma":[0.00104351,0.000357359,0.0004034531,0.0004163752,0.0002443202,0.0006492065,0.0004772598,0.0007357807,0.0005437671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004015099,"about_ca_system_score_gemma":0.0005256372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003578124,"about_ca_topic_score_gemma":0.006306151,"domain_scores_codex":[0.9998757,0.00002016829,0.000006483362,0.0000394287,0.00004023755,0.00001804405],"domain_scores_gemma":[0.9996657,0.0001675812,0.00003202707,0.00002754302,0.00009370386,0.00001340269],"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":[0.0003369394,0.0001043538,0.0008694438,0.0001583997,0.00008737016,0.00009791351,0.00006949117,0.2857532,0.1449252,0.003059548,0.001830872,0.5627073],"study_design_scores_gemma":[0.000006296963,0.00002481774,0.0002788718,0.000006015903,0.0000144452,0.00002289785,0.000007855927,0.9739363,0.02384695,0.001187425,0.0006615143,0.000006633486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03465605,0.0003288405,0.9613475,0.0001888491,0.00008855384,0.00003605933,0.000101518,0.001468405,0.001784165],"genre_scores_gemma":[0.4674424,0.0003818219,0.5262816,0.0001780551,0.0000938327,0.00007493312,0.0004161834,0.0003436312,0.004787565],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003578124,"threshold_uncertainty_score":0.007114589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.011689226307592,"score_gpt":0.294775281898082,"score_spread":0.28308605559049,"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."}}