{"id":"W4226371385","doi":"10.48550/arxiv.2201.02604","title":"Deep Ultrasound Denoising Without Clean Data","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Ultrasound Imaging and Elastography","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Noise reduction; Computer science; Rendering (computer graphics); Imaging phantom; Artificial intelligence; Noise (video); Transmission (telecommunications); Computer vision; Data transmission; Gaussian noise; Telecommunications; Image (mathematics); Optics; Physics; Computer hardware","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":[0.000652916,0.0009395065,0.0009163289,0.0003599234,0.0002088489,0.0006602618,0.0008326819,0.001477106,0.001471457],"category_scores_gemma":[0.001775543,0.0005090481,0.0008427804,0.0003391092,0.0006756198,0.0008550806,0.001203074,0.001359646,0.0008017027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003611057,"about_ca_system_score_gemma":0.0006538471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00242781,"about_ca_topic_score_gemma":0.002811647,"domain_scores_codex":[0.999731,0.0000520894,0.00001734338,0.00007930877,0.00008334308,0.00003682879],"domain_scores_gemma":[0.9996044,0.0001518052,0.00004417876,0.00009393333,0.00008357575,0.00002212703],"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":[0.0003390792,0.0001041624,0.0008373743,0.0003121216,0.0001386191,0.0002786349,0.0001979321,0.61316,0.07237238,0.01343895,0.003699182,0.2951216],"study_design_scores_gemma":[0.000004701029,0.00003850859,0.000176095,0.0000104821,0.00001085331,0.00006771597,0.000009081793,0.9834959,0.01163329,0.003457081,0.00108765,0.000008665933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01278105,0.0002772459,0.9850885,0.0001618019,0.00003464746,0.00002014651,0.00007067137,0.0006082352,0.0009575812],"genre_scores_gemma":[0.4956804,0.0009156974,0.4896378,0.000483511,0.0001094239,0.0001604713,0.0008604002,0.0002673527,0.01188482],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00242781,"threshold_uncertainty_score":0.004922509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07933420891344167,"score_gpt":0.2273122584606624,"score_spread":0.1479780495472207,"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."}}