{"id":"W2914410118","doi":"10.1109/jbhi.2018.2865450","title":"Convolutional Neural Network With Shape Prior Applied to Cardiac MRI Segmentation","year":2018,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":209,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Segmentation; Convolutional neural network; Sørensen–Dice coefficient; Artificial intelligence; Ventricle; Endocardium; Magnetic resonance imaging; Cardiac magnetic resonance imaging; Deep learning; Hausdorff distance; Pattern recognition (psychology); Image segmentation; Computer vision; Medicine; Radiology; Cardiology","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":[0.001375201,0.0001066752,0.0002716661,0.0001539953,0.0001850608,0.00008347753,0.000296539,0.00005420437,0.00002342605],"category_scores_gemma":[0.00001802147,0.00007268497,0.00002949205,0.0003763561,0.0002175676,0.0004296955,0.00006493035,0.0002088364,0.00001300777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008309844,"about_ca_system_score_gemma":0.0003792325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003882681,"about_ca_topic_score_gemma":0.000001060174,"domain_scores_codex":[0.9978233,0.0000392024,0.0009654253,0.00007667943,0.0007998139,0.0002956041],"domain_scores_gemma":[0.9983487,0.00006620726,0.0005849809,0.0001149071,0.0002213425,0.0006638924],"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":[0.00008366134,0.00007784444,0.0003149064,0.000204067,0.00005667274,0.000005473702,0.005943475,0.00004331633,0.0002284394,0.001099618,0.1286485,0.8632941],"study_design_scores_gemma":[0.01968277,0.05499731,0.06082791,0.003736506,0.0002420569,0.002758932,0.006539503,0.6252463,0.01858686,0.009395127,0.1947038,0.003282931],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007251923,0.00005155136,0.9844753,0.00721837,0.0006160167,0.0002574279,0.000003405532,0.00003740966,0.00008862284],"genre_scores_gemma":[0.04321811,0.0001404833,0.9383903,0.01717864,0.001040527,0.000008297341,0.000004662902,0.000006049299,0.00001293025],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8600111,"threshold_uncertainty_score":0.2964007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02378500703133865,"score_gpt":0.3144664781195526,"score_spread":0.290681471088214,"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."}}