{"id":"W4413010725","doi":"10.1109/tmi.2025.3596247","title":"Collaborative Learning of Augmentation and Disentanglement for Semi-Supervised Domain Generalized Medical Image Segmentation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; China Scholarship Council; Natural Science Foundation of Liaoning Province; National Natural Science Foundation of China","keywords":"Image segmentation; Segmentation; Artificial intelligence; Computer science; Image (mathematics); Domain (mathematical analysis); Computer vision; Medical imaging; Scale-space segmentation; 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":[0.001070944,0.0001966741,0.0002906176,0.0003219519,0.0002630191,0.00009862134,0.0003821669,0.00009556148,0.0003101672],"category_scores_gemma":[0.0001727789,0.0001867659,0.00008750497,0.0006170993,0.0002904363,0.0005162077,0.00001374252,0.0003053904,0.000002589991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001286826,"about_ca_system_score_gemma":0.0003253366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003142031,"about_ca_topic_score_gemma":0.00001078087,"domain_scores_codex":[0.9971709,0.0003224539,0.0006457423,0.0004602352,0.001129749,0.0002708776],"domain_scores_gemma":[0.9985764,0.0005616935,0.0001487545,0.0002148238,0.0002166966,0.0002816389],"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":[0.0001213187,0.0004398457,0.0001554816,0.0002737734,0.0001472939,0.00002699023,0.002424712,0.000089617,0.07486918,0.00214399,0.002244543,0.9170632],"study_design_scores_gemma":[0.006277434,0.0001790363,0.00008672091,0.0005718654,0.00008375986,0.00001402678,0.002320004,0.3725785,0.6149814,0.00223468,0.0003452152,0.000327295],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004042963,0.0001077007,0.9877163,0.006557703,0.0004231605,0.0007530817,0.00001453622,0.0002086676,0.0001759051],"genre_scores_gemma":[0.2944699,0.0007345396,0.6976575,0.005713366,0.00007558699,0.0009190963,0.00005692405,0.00003662154,0.0003365147],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9167359,"threshold_uncertainty_score":0.761609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007367527850164544,"score_gpt":0.3121428772606518,"score_spread":0.3047753494104873,"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."}}