{"id":"W3000054715","doi":"10.1002/mp.14022","title":"Fully automated segmentation of left ventricular scar from 3D late gadolinium enhancement magnetic resonance imaging using a cascaded multi‐planar U‐Net (CMPU‐Net)","year":2020,"lang":"en","type":"article","venue":"Medical Physics","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"Libin Cardiovascular Institute of Alberta; University of Guelph; University of Calgary; Imperial College of Toronto; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Magnetic resonance imaging; Segmentation; Computer science; Hausdorff distance; Ventricle; Sørensen–Dice coefficient; Artificial intelligence; Image segmentation; Voxel; Nuclear medicine; Medicine; Sagittal plane; Radiology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006154276,0.001039197,0.0006554424,0.0009247001,0.0003445361,0.0005515374,0.0008498082,0.0008609593,0.0009956164],"category_scores_gemma":[0.0007597227,0.0005646535,0.0008496863,0.0003610723,0.0003036784,0.0005530537,0.0007288665,0.0004295384,0.0004440757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005215038,"about_ca_system_score_gemma":0.0008224138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006416096,"about_ca_topic_score_gemma":0.01177533,"domain_scores_codex":[0.9997904,0.00002796203,0.00001121022,0.00008424024,0.00004745845,0.00003878651],"domain_scores_gemma":[0.9997607,0.0000777657,0.00003939162,0.00002884631,0.00007108604,0.00002225209],"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":[0.0008808856,0.0002163867,0.008619223,0.0002415514,0.0002673413,0.0008177,0.0001857748,0.2391127,0.1255864,0.0007920799,0.00276741,0.6205125],"study_design_scores_gemma":[0.00001173559,0.000114123,0.003235409,0.00001631866,0.00004889656,0.0002080409,0.00002980195,0.9739922,0.02124828,0.0004482573,0.0006338754,0.00001317479],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2893806,0.0009525286,0.7027771,0.0001330057,0.00007309745,0.0002667063,0.0003751393,0.004188093,0.001853804],"genre_scores_gemma":[0.6086463,0.0003567037,0.3867195,0.0001257356,0.00003139206,0.0001366289,0.0009966929,0.0001695036,0.002817495],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006416096,"threshold_uncertainty_score":0.01275748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02369097159841551,"score_gpt":0.3182699504666641,"score_spread":0.2945789788682486,"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."}}