{"id":"W4379390605","doi":"10.32920/23296367","title":"An automatic approach to fetal magnetic resonance image segmentation using 2D U-Net Architecture","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Fetal and Pediatric Neurological Disorders","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Magnetic resonance imaging; Convolutional neural network; Artificial intelligence; Computer science; Sørensen–Dice coefficient; Image segmentation; Pattern recognition (psychology); Medicine; Computer vision; 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":[0.0005609505,0.0008094318,0.000472537,0.0007695771,0.0004439641,0.001051976,0.001378442,0.001161495,0.002614459],"category_scores_gemma":[0.001023628,0.0005149826,0.0006735323,0.0004535799,0.0004247816,0.0007782343,0.0009976531,0.001006451,0.001154107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001215069,"about_ca_system_score_gemma":0.001376868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01187371,"about_ca_topic_score_gemma":0.01737531,"domain_scores_codex":[0.9997885,0.00003050904,0.00001220916,0.00006898443,0.00006430608,0.00003556956],"domain_scores_gemma":[0.9997852,0.00006059332,0.00002410038,0.0000324522,0.00007953145,0.00001811046],"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":[0.0002769535,0.0001136157,0.002277784,0.0001035464,0.00008535219,0.0002118386,0.0001310656,0.3172294,0.02959325,0.0103029,0.007622928,0.6320513],"study_design_scores_gemma":[0.000004038779,0.00002884205,0.0002280827,0.00001113177,0.000007931791,0.00004784002,0.000009499232,0.9883846,0.007780561,0.001920791,0.001568965,0.000007707208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02193766,0.0003415407,0.9703964,0.0003226059,0.00007469869,0.00008947044,0.00021389,0.00367055,0.002953225],"genre_scores_gemma":[0.25968,0.000444854,0.7286484,0.000392466,0.00004949714,0.000197691,0.001149278,0.0004414569,0.008996322],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01187371,"threshold_uncertainty_score":0.02360922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03789283883999169,"score_gpt":0.3007410615468319,"score_spread":0.2628482227068403,"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."}}