{"id":"W4404307300","doi":"10.1109/access.2024.3496907","title":"Speckle Noise Reduction for Medical Ultrasound Images Using Hybrid CNN-Transformer Network","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Speckle noise; Computer science; Noise reduction; Speckle pattern; Artificial intelligence; Ultrasound; Medical ultrasound; Reduction (mathematics); Computer vision; Transformer; Acoustics; Electrical engineering; Voltage; Engineering; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001221765,0.0001686266,0.000196227,0.0001101105,0.0002353169,0.001295503,0.0009902428,0.00007503913,0.00008188852],"category_scores_gemma":[0.00007526139,0.000147776,0.0001421161,0.0005006345,0.00008120989,0.001871172,0.0000486922,0.0002199838,0.00002526614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000588301,"about_ca_system_score_gemma":0.0002131866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006160902,"about_ca_topic_score_gemma":0.00000192533,"domain_scores_codex":[0.9982236,0.0001003125,0.0003215389,0.0004907424,0.000429279,0.000434503],"domain_scores_gemma":[0.9990469,0.0003614084,0.00004322952,0.0003248602,0.00009135892,0.0001322411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001356356,0.0001621684,0.0001034589,0.0004973657,0.0002331698,0.0005978446,0.0007982394,0.005287119,0.2817249,0.007065937,0.3112674,0.3921268],"study_design_scores_gemma":[0.001008844,0.0001297981,0.0001807307,0.0005143289,0.0001280001,0.001667935,0.0000140412,0.170794,0.6844663,0.08940863,0.05079167,0.0008957345],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01289592,0.0008914138,0.9779258,0.000692316,0.006153948,0.0002315773,0.000006634559,0.000247312,0.0009550476],"genre_scores_gemma":[0.6673406,0.0001922945,0.3231632,0.001022702,0.006961947,0.00004649736,0.00001640475,0.00007066443,0.001185674],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6547626,"threshold_uncertainty_score":0.9997413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03912937960486881,"score_gpt":0.3588709546140167,"score_spread":0.3197415750091479,"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."}}