{"id":"W4410048232","doi":"10.1016/j.bspc.2025.107956","title":"Pseudo Label-Guided Data Fusion and output consistency for semi-supervised medical image segmentation","year":2025,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Consistency (knowledge bases); Artificial intelligence; Computer science; Segmentation; Fusion; Image (mathematics); Pattern recognition (psychology); Computer vision; Image fusion; Image segmentation","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":[0.001349176,0.0001880345,0.0003115113,0.0001497182,0.0003294737,0.0003242992,0.0007265296,0.0001873232,0.00003706433],"category_scores_gemma":[0.0006446055,0.0001498977,0.00002668142,0.0003054549,0.0004989051,0.0005830213,0.0003909287,0.0001818371,0.000001961851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002709871,"about_ca_system_score_gemma":0.0004410422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001996527,"about_ca_topic_score_gemma":0.000001446077,"domain_scores_codex":[0.9976683,0.0001275545,0.0005278483,0.0006789079,0.0006886992,0.0003086797],"domain_scores_gemma":[0.9985726,0.0004516489,0.0001227183,0.0003061369,0.0001757218,0.0003711711],"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":[0.00003304955,0.0001147157,0.00006647067,0.0002762355,0.00002626806,0.0000123004,0.0001064056,1.743185e-8,0.02730861,0.0002757758,0.009536003,0.9622442],"study_design_scores_gemma":[0.008793388,0.0003029682,0.0002121326,0.0006760005,0.0001172944,0.00005053727,0.0001591001,0.9761616,0.005638875,0.004311512,0.00320858,0.0003680331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001031586,0.001332489,0.9851978,0.01141397,0.0001064107,0.0005040132,0.00003603916,0.0002457776,0.0001319454],"genre_scores_gemma":[0.5885895,0.0003408313,0.392733,0.01704738,0.000299845,0.0002621775,0.0002837332,0.00002585078,0.0004176903],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9761615,"threshold_uncertainty_score":0.6112651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03138742140786215,"score_gpt":0.3276798020295956,"score_spread":0.2962923806217334,"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."}}