{"id":"W4386625561","doi":"10.18280/isi.280426","title":"Enhanced Speckle Noise Reduction in Breast Cancer Ultrasound Imagery Using a Hybrid Deep Learning Model","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Speckle noise; Ultrasound; Noise reduction; Noise (video); Breast cancer; Reduction (mathematics); Speckle pattern; Computer science; Artificial intelligence; Medicine; Cancer; Radiology; Internal medicine; Image (mathematics); Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009416986,0.0001859823,0.0002198744,0.0006104975,0.0003194148,0.0005462532,0.000325077,0.00006865582,0.00001269074],"category_scores_gemma":[0.0001653802,0.0001976004,0.00007055956,0.001321221,0.00007232371,0.006810509,0.0001144315,0.0002458277,0.00007608841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004781106,"about_ca_system_score_gemma":0.0001498033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002417139,"about_ca_topic_score_gemma":0.000004055877,"domain_scores_codex":[0.9983255,0.0001443575,0.0005424425,0.0002241093,0.0003241848,0.0004393639],"domain_scores_gemma":[0.9990997,0.00007988767,0.0002599487,0.000261597,0.0002287983,0.00007002915],"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":[0.0000584363,0.00001960064,0.0002637213,0.000178181,0.00001807021,0.0000161453,0.01344134,0.6327143,0.1314697,0.0005206789,0.000137709,0.2211621],"study_design_scores_gemma":[0.0003894281,0.00001357158,0.002678235,0.0001724357,0.000006974286,0.000241298,0.0003469066,0.9708311,0.01984713,0.005194569,0.00002165672,0.0002566765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3590778,0.00003505333,0.6392943,0.00003489859,0.0003024323,0.0001283266,0.000005142619,0.0002581326,0.0008639374],"genre_scores_gemma":[0.9652442,0.00009527594,0.03431471,0.00007262982,0.00009140822,0.00003685226,0.00002861549,0.00001411966,0.0001021978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6061664,"threshold_uncertainty_score":0.805791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01982247873710845,"score_gpt":0.2703413217672067,"score_spread":0.2505188430300982,"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."}}