{"id":"W4377142661","doi":"10.1109/tnnls.2023.3269223","title":"Fuzzy Attention Neural Network to Tackle Discontinuity in Airway Segmentation","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"NIHR Imperial Biomedical Research Centre; National Natural Science Foundation of China; Medical Research Council; Royal Society; Nvidia; British Heart Foundation; National Institute for Health and Care Research; Horizon 2020 Framework Programme; Eusko Jaurlaritza; UK Research and Innovation; Boehringer Ingelheim","keywords":"Computer science; Robustness (evolution); Segmentation; Artificial intelligence; Fuzzy logic; Pattern recognition (psychology); Feature (linguistics); Artificial neural network","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":[0.0005822773,0.0002334228,0.0003836115,0.0002908495,0.0003602819,0.0001237734,0.00006360601,0.0001338683,0.0000116404],"category_scores_gemma":[0.00001956514,0.0002219457,0.0001139808,0.001121483,0.00003434564,0.0001541326,0.000003731012,0.0007663164,0.00003319934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001301372,"about_ca_system_score_gemma":0.00001745233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004917491,"about_ca_topic_score_gemma":0.0002072492,"domain_scores_codex":[0.9979521,0.0003585219,0.0004305053,0.0004835069,0.0002787557,0.0004966151],"domain_scores_gemma":[0.9990644,0.0003897201,0.0001031044,0.0002008437,0.00004890674,0.0001930688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001566734,0.00005866523,0.007494142,0.00008333022,0.00002555255,0.00003732415,0.0002769342,0.961628,0.0004875402,0.000002841707,0.002262575,0.02748639],"study_design_scores_gemma":[0.001265228,0.0006316163,0.03471747,0.0006438274,0.00008475115,0.0000378954,0.0004677203,0.9596493,0.00002602929,0.000002065681,0.002200516,0.0002735832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9555974,0.0001966603,0.03429613,0.005303336,0.003003394,0.001138193,0.000004271821,0.0004301106,0.00003050755],"genre_scores_gemma":[0.996001,0.0001049217,0.00002817296,0.001226262,0.0004588211,0.0001805632,0.00002400336,0.00004851917,0.001927741],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0404036,"threshold_uncertainty_score":0.9050683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0219467029020846,"score_gpt":0.2926499165752606,"score_spread":0.270703213673176,"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."}}