{"id":"W4406785230","doi":"10.48550/arxiv.2501.13193","title":"Revisiting Data Augmentation for Ultrasound Images","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Ultrasound; Computer vision; Computer science; Artificial intelligence; Computer graphics (images); Medicine; Radiology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00101886,0.0002508426,0.0003047025,0.0001507898,0.0001498833,0.0003373918,0.00318673,0.0001634738,0.00004472249],"category_scores_gemma":[0.001298973,0.000258869,0.00008935938,0.0002050942,0.00006776782,0.0007325191,0.003056477,0.0003872661,0.00002924549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001024642,"about_ca_system_score_gemma":0.0002393327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005858952,"about_ca_topic_score_gemma":0.000001936235,"domain_scores_codex":[0.9976068,0.0001283951,0.0005458622,0.001093352,0.0003416761,0.000283914],"domain_scores_gemma":[0.996402,0.0006994383,0.0003671453,0.00223466,0.0002042042,0.00009254894],"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":[0.00002882904,0.0002373037,0.05342511,0.004012927,0.0004255645,0.00003877183,0.001386776,0.00006146921,0.04979362,0.002913613,0.209845,0.6778311],"study_design_scores_gemma":[0.002617487,0.0001887748,0.06517348,0.004982897,0.0005174504,0.00003014666,0.0004074291,0.02537251,0.8622319,0.022561,0.01287514,0.003041797],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002068536,0.00032511,0.9926488,0.001660593,0.000762505,0.0009041692,0.0002294123,0.0006032109,0.0007976266],"genre_scores_gemma":[0.02085384,0.0004535125,0.9711455,0.002647298,0.0005781282,0.000335087,0.001966545,0.00002408673,0.001996083],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8124382,"threshold_uncertainty_score":0.9999864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1087417542689535,"score_gpt":0.3885910580925978,"score_spread":0.2798493038236443,"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."}}