{"id":"W2941524851","doi":"10.1109/tmi.2019.2930068","title":"Reducing the Hausdorff Distance in Medical Image Segmentation With Convolutional Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"IEEE Transactions on Medical Imaging","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Prostate Cancer Canada","keywords":"Hausdorff distance; Segmentation; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Scale-space segmentation; Computer science; Image segmentation; Segmentation-based object categorization; Computer vision; Similarity (geometry); Boundary (topology); Mathematics; Image (mathematics)","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007695273,0.0004259228,0.0004008875,0.0001824735,0.0003558642,0.0002112191,0.001934326,0.0002457572,0.000146002],"category_scores_gemma":[0.00004063616,0.0003182949,0.0001437615,0.0007400399,0.0005716122,0.0004999163,0.00006102952,0.003534754,0.00002667871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003191955,"about_ca_system_score_gemma":0.000500674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009067291,"about_ca_topic_score_gemma":0.0001342953,"domain_scores_codex":[0.9953458,0.0003060327,0.0006917557,0.001117302,0.001905634,0.0006334634],"domain_scores_gemma":[0.9972121,0.0009291475,0.0002641879,0.001126252,0.0001216569,0.0003466718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004051959,0.0001700025,0.00009388828,0.00004007402,0.00003311839,0.0001237528,0.0002317418,0.8457518,0.00003443922,0.0006118162,0.000476919,0.152392],"study_design_scores_gemma":[0.0007006585,0.00001940666,0.0002389616,0.0004931783,0.00002218666,0.0001553604,0.00004613076,0.997116,0.0001567331,0.0005396488,0.000170554,0.0003411582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001320191,0.0003033709,0.9724064,0.02300109,0.001718793,0.000821479,0.00001167536,0.0002541153,0.0001628204],"genre_scores_gemma":[0.980858,0.0002810158,0.01510736,0.002777384,0.000302152,0.0005057289,0.00002707319,0.00004826826,0.00009296647],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9795378,"threshold_uncertainty_score":0.9999269,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01141282055493615,"score_gpt":0.2807220776232556,"score_spread":0.2693092570683195,"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."}}