{"id":"W4378979186","doi":"10.1016/j.neucom.2023.126411","title":"Mutually aided uncertainty incorporated dual consistency regularization with pseudo label for semi-supervised medical image segmentation","year":2023,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Central South University; Natural Science Foundation of Hunan Province; Royal Society","keywords":"Artificial intelligence; Regularization (linguistics); Computer science; Consistency (knowledge bases); Dual (grammatical number); Segmentation; Image segmentation; Computer vision; Image (mathematics); Pattern recognition (psychology); 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":[],"consensus_categories":[],"category_scores_codex":[0.001002963,0.0002419393,0.0002692839,0.0002536921,0.0003410787,0.0002532958,0.0005883597,0.0001249134,0.0000259919],"category_scores_gemma":[0.0006772494,0.0002189052,0.00005275007,0.001503798,0.0001434475,0.0005959234,0.0003033336,0.0002383318,0.00002903674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006722264,"about_ca_system_score_gemma":0.0003586132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001707753,"about_ca_topic_score_gemma":0.000006211963,"domain_scores_codex":[0.9969926,0.0002452596,0.0006055894,0.0007004787,0.001006571,0.0004495129],"domain_scores_gemma":[0.9980262,0.0005956242,0.0002998889,0.0003965026,0.0004378732,0.000243923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002094099,0.000583494,0.001192322,0.0007228924,0.0001722129,0.0009864728,0.004652837,0.006807641,0.3360322,0.01234578,0.02648868,0.6098061],"study_design_scores_gemma":[0.002070632,0.0003347061,0.000327469,0.000123894,0.00001537328,0.00006297847,0.0001261178,0.9659466,0.02936151,0.001317383,0.00004066421,0.0002726385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03420331,0.000004181812,0.9607714,0.001867481,0.0002245488,0.0009661505,0.000006507316,0.00176137,0.0001949861],"genre_scores_gemma":[0.106842,0.00001307784,0.8876129,0.004340856,0.0002480735,0.0002164748,0.000410667,0.00007275304,0.0002431724],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.959139,"threshold_uncertainty_score":0.8926697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02510026807953412,"score_gpt":0.2913326148051888,"score_spread":0.2662323467256547,"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."}}