{"id":"W2791267892","doi":"10.1117/12.2293518","title":"Myocardial scar segmentation from magnetic resonance images using convolutional neural network","year":2018,"lang":"en","type":"article","venue":"Medical Imaging 2018: Computer-Aided Diagnosis","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Carleton University","funders":"","keywords":"Segmentation; Convolutional neural network; Artificial intelligence; Computer science; Magnetic resonance imaging; Pattern recognition (psychology); Image segmentation; Sørensen–Dice coefficient; Pooling; Benchmark (surveying); Computer vision; Medicine; Radiology","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":[0.0006181794,0.0007637285,0.0004797122,0.001508905,0.0002032655,0.0006578724,0.0006378323,0.0007059762,0.0005689903],"category_scores_gemma":[0.001195316,0.0004051794,0.000595008,0.000722637,0.0002303156,0.0005889573,0.0004650685,0.0003867884,0.0003080824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005780713,"about_ca_system_score_gemma":0.0005652576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006572106,"about_ca_topic_score_gemma":0.01152088,"domain_scores_codex":[0.9997217,0.00004021175,0.00002482367,0.00007569055,0.00009163589,0.0000459976],"domain_scores_gemma":[0.9996328,0.0001125508,0.0000882198,0.00004878515,0.0001012047,0.00001644221],"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":[0.0004108848,0.0001493643,0.0114895,0.0003084722,0.0002648551,0.0005986051,0.0001451173,0.1348941,0.1531075,0.001450258,0.002257448,0.6949239],"study_design_scores_gemma":[0.000009817591,0.00005904419,0.006294294,0.00002808556,0.00005521513,0.0002981778,0.00001869289,0.9567455,0.03435712,0.0009605028,0.001156162,0.00001726747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1723362,0.001612747,0.8211619,0.000185301,0.00005323645,0.0001252528,0.0002968914,0.002487753,0.00174079],"genre_scores_gemma":[0.6680835,0.001210332,0.3271561,0.0001699001,0.00004918355,0.00009239706,0.0009381449,0.0001499282,0.002150515],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006572106,"threshold_uncertainty_score":0.01306766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01577843774063472,"score_gpt":0.2816052026859854,"score_spread":0.2658267649453507,"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."}}