{"id":"W4416040400","doi":"10.1016/j.media.2025.103857","title":"Adaptive mix for semi-supervised medical image segmentation","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National University's Basic Research Foundation of China; China Scholarship Council; Natural Science Foundation of Liaoning Province; National Natural Science Foundation of China","keywords":"Overfitting; Segmentation; Perturbation (astronomy); Image segmentation; Pattern recognition (psychology); Image (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001805029,0.0009156639,0.001512992,0.001601338,0.0006534592,0.001400758,0.002269492,0.001871182,0.004100872],"category_scores_gemma":[0.002930824,0.0009853392,0.00124235,0.001228677,0.0008918726,0.001651985,0.002859012,0.001398831,0.001799068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008290941,"about_ca_system_score_gemma":0.001247931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001876198,"about_ca_topic_score_gemma":0.004684005,"domain_scores_codex":[0.9988073,0.0002941455,0.00007003787,0.0003156495,0.0003963634,0.0001164579],"domain_scores_gemma":[0.9987399,0.0005478512,0.0001284965,0.0002174399,0.0002795644,0.00008677283],"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":[0.001346957,0.0002583462,0.001750822,0.0003684754,0.0003218681,0.0001522332,0.0002504207,0.1054634,0.08558996,0.00959795,0.004860079,0.7900395],"study_design_scores_gemma":[0.00001842768,0.000107422,0.0006012755,0.0000149668,0.00003412146,0.000136971,0.00003031944,0.9700095,0.02085976,0.005847091,0.002322914,0.00001734665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01755254,0.0003268732,0.9789734,0.0001197149,0.0000372431,0.00010169,0.0001669028,0.001971374,0.0007502645],"genre_scores_gemma":[0.2372527,0.0002743852,0.753057,0.0002736415,0.0001392354,0.0003632058,0.0009028426,0.0007816048,0.006955365],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004100872,"threshold_uncertainty_score":0.01371872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01263338003916533,"score_gpt":0.3177888244760969,"score_spread":0.3051554444369315,"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."}}