{"id":"W4367145552","doi":"10.1121/10.0019119","title":"A preliminary numerical investigation of convolutional neural network (CNN) techniques for filtering high-intensity focused ultrasound (HIFU) noise in images","year":2023,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Ultrasound Imaging and Elastography","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Convolutional neural network; Computer science; Ultrasound; High-intensity focused ultrasound; Artificial intelligence; Deep learning; Ultrasound energy; Noise (video); Filter (signal processing); Noise reduction; Ultrasonic sensor; Artificial neural network; Acoustics; Computer vision; Image (mathematics); Physics","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":[0.000721657,0.0005211006,0.0004084934,0.0003325694,0.0002939468,0.0004494711,0.0005791619,0.001020615,0.0026375],"category_scores_gemma":[0.00330809,0.000229709,0.0004926294,0.000314194,0.0004300921,0.0005090648,0.0003281369,0.0006989684,0.00019826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008087743,"about_ca_system_score_gemma":0.0007064662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01671235,"about_ca_topic_score_gemma":0.01384599,"domain_scores_codex":[0.9998597,0.00003453162,0.000009475199,0.00002346007,0.00004631589,0.00002649515],"domain_scores_gemma":[0.9991236,0.0004982032,0.00007116225,0.00005060791,0.0002256374,0.00003081974],"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":[0.00007804453,0.00004490654,0.001742098,0.0001090578,0.00002351798,0.0001185945,0.00003754838,0.9771146,0.005312013,0.003935046,0.0006548466,0.01082979],"study_design_scores_gemma":[0.000003242162,0.00001162125,0.0001134641,0.000005130787,0.000002401637,0.000009333593,0.000003463473,0.9987921,0.0006736501,0.0002195196,0.0001643331,0.000001742019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4311502,0.002283299,0.5355173,0.00226109,0.0003053269,0.0002515921,0.0007817524,0.001240826,0.02620847],"genre_scores_gemma":[0.8808548,0.0004465894,0.114086,0.000155398,0.00002394086,0.0001182587,0.0002724259,0.00008518822,0.003957323],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01671235,"threshold_uncertainty_score":0.03323013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01396848326948671,"score_gpt":0.2533797308114972,"score_spread":0.2394112475420105,"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."}}