{"id":"W4409653850","doi":"10.1016/j.engappai.2025.110786","title":"Dual-phase airway segmentation: Enhancing distal bronchial identification with anatomical prior guidance","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Airway Management and Intubation Techniques","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Science Foundation of Fujian Province; National Natural Science Foundation of China; Fuzhou Science and Technology Bureau","keywords":"Computer science; Segmentation; Dual (grammatical number); Identification (biology); Artificial intelligence; Airway; Phase (matter); Pattern recognition (psychology); Computer vision; Medicine; Surgery","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":[0.0002065176,0.000138599,0.0001916836,0.0002758755,0.00009399658,0.00003421181,0.0001291927,0.0000592465,0.0001188497],"category_scores_gemma":[0.00007565536,0.0001380884,0.0000565985,0.0007364338,0.00009096047,0.0001360448,0.00003700462,0.0001281837,0.00002108754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009094921,"about_ca_system_score_gemma":0.00006835075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000142413,"about_ca_topic_score_gemma":0.000007796628,"domain_scores_codex":[0.9987579,0.000009546637,0.0005937347,0.0002844533,0.0002050543,0.0001492886],"domain_scores_gemma":[0.999159,0.00006112328,0.0001368569,0.0003796744,0.0002112004,0.00005207808],"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":[0.000262969,0.0008031453,0.0001901253,0.0005154017,0.0001382487,9.393114e-7,0.0004121477,0.003545166,0.2983071,0.1772524,0.001077928,0.5174944],"study_design_scores_gemma":[0.0001162486,0.0002679747,0.0002814363,0.0001510356,0.0000807762,9.91498e-7,0.0002558778,0.03223794,0.9613956,0.0006990469,0.004366674,0.0001463724],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06579927,0.0001144512,0.9315748,0.0004206221,0.00007247719,0.000885833,0.000008575456,0.0002150256,0.000908984],"genre_scores_gemma":[0.9727242,0.00005534926,0.02514995,0.00001839826,0.00009043007,0.0004675389,0.00006572714,0.00001699062,0.001411439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9069249,"threshold_uncertainty_score":0.5631081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01053029688156178,"score_gpt":0.3102184012068937,"score_spread":0.2996881043253319,"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."}}