{"id":"W4380758096","doi":"10.1016/j.inffus.2023.101880","title":"FTransCNN: Fusing Transformer and a CNN based on fuzzy logic for uncertain medical image segmentation","year":2023,"lang":"en","type":"article","venue":"Information Fusion","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":104,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"China Postdoctoral Science Foundation; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Segmentation; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Fuzzy logic; Transformer; Scale-space segmentation; Image segmentation; Computer vision","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":[0.0006484366,0.0001400921,0.0001766132,0.0004102347,0.0001833658,0.00005524407,0.0000502897,0.0001433246,0.0002124292],"category_scores_gemma":[0.0004051294,0.0001191942,0.0000777821,0.0003973025,0.00005159255,0.0004525671,0.00000867244,0.0001279461,0.0001237278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000122992,"about_ca_system_score_gemma":0.0001831473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003476463,"about_ca_topic_score_gemma":0.00000756834,"domain_scores_codex":[0.9986194,0.00002579513,0.0003920812,0.0001424322,0.0005975833,0.0002226759],"domain_scores_gemma":[0.9991645,0.0003452394,0.00008307125,0.0001347337,0.0001274071,0.0001450613],"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":[0.002925009,0.0004086494,0.00116803,0.004281296,0.0000655791,0.00004620488,0.01109393,0.003935701,0.05004708,0.001401612,0.0564307,0.8681962],"study_design_scores_gemma":[0.01840263,0.001765472,0.01179779,0.001767125,0.0002171811,0.00003686085,0.002049207,0.808744,0.02071415,0.0008970741,0.1329907,0.0006178328],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4835571,0.00004801166,0.1892016,0.3131203,0.0009262055,0.00540322,0.0001637862,0.001336282,0.006243552],"genre_scores_gemma":[0.889158,0.0002476818,0.007709553,0.099857,0.000217619,0.0003499329,0.002310919,0.00004146124,0.0001079198],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8675784,"threshold_uncertainty_score":0.4860597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03324935523160569,"score_gpt":0.345530683033493,"score_spread":0.3122813278018873,"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."}}