{"id":"W4416386195","doi":"10.1145/3777481","title":"DPANet: Domain Pyramid Attention Network for Domain Generalization on Medical Image Segmentation in Connected Health","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Computing for Healthcare","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Segmentation; Pyramid (geometry); Image segmentation; Domain (mathematical analysis); Similarity (geometry); Generalization; Domain knowledge; Key (lock)","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":[0.001095684,0.0001940596,0.0004466907,0.0003790038,0.0005363283,0.00003277708,0.0001182741,0.0001454837,0.00001312404],"category_scores_gemma":[0.0001395124,0.0001933495,0.0002052338,0.0007660964,0.00004799761,0.00004642552,0.000004300672,0.0003028504,0.000002727853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004517978,"about_ca_system_score_gemma":0.0003256964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004896488,"about_ca_topic_score_gemma":0.0005496441,"domain_scores_codex":[0.9978362,0.0002343587,0.000689291,0.0004644996,0.00031407,0.0004615505],"domain_scores_gemma":[0.9986361,0.0004846304,0.0001772475,0.0003256893,0.0002076472,0.0001686499],"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":[0.0050728,0.002339524,0.02827716,0.008675253,0.0008130633,0.0000320328,0.003224914,0.05283527,0.002744435,0.01264118,0.01139511,0.8719493],"study_design_scores_gemma":[0.04219882,0.008879504,0.08303921,0.02015567,0.0006956137,0.0001089187,0.007694778,0.7729901,0.002459028,0.04713522,0.01294407,0.001699086],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1461287,0.0001620595,0.759979,0.09186084,0.0003751989,0.001315268,0.00003947614,0.000120957,0.00001857565],"genre_scores_gemma":[0.8656294,0.000133722,0.1222185,0.01027392,0.0002808185,0.0001692735,0.001097888,0.00004305692,0.000153361],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8702502,"threshold_uncertainty_score":0.7884566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02212578672013456,"score_gpt":0.3704749703042126,"score_spread":0.348349183584078,"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."}}