{"id":"W4281621674","doi":"10.3389/fnins.2022.887634","title":"FetalGAN: Automated Segmentation of Fetal Functional Brain MRI Using Deep Generative Adversarial Learning and Multi-Scale 3D U-Net","year":2022,"lang":"en","type":"article","venue":"Frontiers in Neuroscience","topic":"Fetal and Pediatric Neurological Disorders","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Artificial intelligence; Computer science; Segmentation; Convolutional neural network; Sørensen–Dice coefficient; Pattern recognition (psychology); Deep learning; Preprocessor; Voxel; Magnetic resonance imaging; Artificial neural network; Ground truth; Image segmentation; Medicine; Radiology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001387995,0.001512811,0.0006541462,0.0008112678,0.0003136389,0.0009125189,0.001173486,0.00124599,0.00246518],"category_scores_gemma":[0.002433658,0.000568282,0.0009552503,0.0003442903,0.0007407502,0.0007200022,0.001249159,0.001630878,0.0008539159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00102415,"about_ca_system_score_gemma":0.001105992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005832778,"about_ca_topic_score_gemma":0.009438843,"domain_scores_codex":[0.9995937,0.0001186629,0.00001839322,0.000120985,0.0001091486,0.00003917519],"domain_scores_gemma":[0.9994088,0.0003159565,0.00006256967,0.000100077,0.00007818219,0.00003437565],"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":[0.0003990658,0.00007471548,0.002154576,0.0001730553,0.000200807,0.0003479837,0.00009461186,0.7411003,0.01612589,0.005381447,0.01169435,0.2222532],"study_design_scores_gemma":[0.00001207295,0.00003234381,0.0002570685,0.00001364539,0.00001251027,0.0001502481,0.000007845551,0.9893095,0.006422339,0.00242899,0.001338646,0.00001482455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03154937,0.0009053694,0.9544127,0.0005657981,0.000156203,0.0001374339,0.0006650253,0.00927172,0.002336411],"genre_scores_gemma":[0.4668912,0.0007437614,0.520254,0.001121149,0.00008336578,0.0002572222,0.003310007,0.001527459,0.005811764],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005832778,"threshold_uncertainty_score":0.01159769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0192596658595514,"score_gpt":0.2672898538335878,"score_spread":0.2480301879740364,"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."}}