{"id":"W4378070369","doi":"10.1016/j.ultras.2023.107050","title":"Deep-learning-assisted and GPU-accelerated vector Doppler imaging with aliasing-resistant velocity estimation","year":2023,"lang":"en","type":"article","venue":"Ultrasonics","topic":"Ultrasound Imaging and Elastography","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Research Institute for Aging","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canadian Space Agency","keywords":"Aliasing; Computer science; Artificial intelligence; Doppler effect; Convolutional neural network; Computer vision; Vector flow; Pattern recognition (psychology); Segmentation; Filter (signal processing); Image segmentation; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002633874,0.0002464016,0.0003024523,0.0002342914,0.000310852,0.0001398706,0.00006593388,0.00007025954,0.00005248484],"category_scores_gemma":[0.0003343591,0.0002043944,0.00006451342,0.001077941,0.0001775213,0.0001595507,0.00001942953,0.0003798604,0.00004852799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006971629,"about_ca_system_score_gemma":0.0000855455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001008643,"about_ca_topic_score_gemma":0.00002616594,"domain_scores_codex":[0.9985033,0.00005902908,0.000246181,0.0004021883,0.0003394302,0.0004498447],"domain_scores_gemma":[0.9990659,0.0002196152,0.0001101343,0.000229137,0.0001724426,0.0002027306],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001996182,0.0005745121,0.6288539,0.0008369857,0.0008600832,0.0002685227,0.006272932,0.003239739,0.246835,0.0004803269,0.005413963,0.1043678],"study_design_scores_gemma":[0.00275294,0.0003878282,0.8884478,0.0003932604,0.0003360831,0.0006921564,0.00115704,0.09021143,0.001308653,0.00005909313,0.01373956,0.0005141666],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9903219,0.000372617,0.005934445,0.001245497,0.0001287533,0.0002784223,0.000008938109,0.0008562625,0.0008531465],"genre_scores_gemma":[0.9857713,0.0001418396,0.01317895,0.0002124658,0.00005376653,0.0000201991,0.0002355687,0.00005881664,0.0003270968],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2595938,"threshold_uncertainty_score":0.8334962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01383071455137909,"score_gpt":0.2552223444135513,"score_spread":0.2413916298621723,"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."}}