{"id":"W4412805789","doi":"10.1016/j.cmpbup.2025.100211","title":"Robust lung segmentation in Chest X-ray images using modified U-Net with deeper network and residual blocks","year":2025,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine Update","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Residual; Net (polyhedron); Segmentation; X-ray; Computer science; Artificial intelligence; Materials science; Computer vision; Mathematics; Optics; Physics; Geometry; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00182543,0.0002689035,0.0005765975,0.0004825039,0.00008282674,0.00008242674,0.00008816171,0.0001323863,0.000005986552],"category_scores_gemma":[0.00003939949,0.000208315,0.00002373187,0.001127415,0.0003111235,0.0000977504,0.0001638745,0.0003120269,1.501088e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007744833,"about_ca_system_score_gemma":0.00009506726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002672675,"about_ca_topic_score_gemma":0.00004629549,"domain_scores_codex":[0.9980348,0.0003265303,0.000470229,0.00058718,0.0001794959,0.0004017437],"domain_scores_gemma":[0.9990724,0.0003571961,0.0001057103,0.0002702076,0.00007136745,0.0001231278],"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":[0.0004759579,0.0003164417,0.2754997,0.0008802825,0.0001584368,0.0002007674,0.001038497,0.003372791,0.001098848,0.0001066032,0.002397326,0.7144543],"study_design_scores_gemma":[0.02196085,0.001883759,0.3816114,0.01117583,0.001002797,0.0002172963,0.0006161969,0.5608173,0.001082693,0.001910883,0.01663691,0.001084093],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3702185,0.003841414,0.6139463,0.01047699,0.0003031977,0.001112474,0.0000021312,0.00007732811,0.00002171893],"genre_scores_gemma":[0.05748335,0.0004081132,0.9365308,0.005099523,0.0003012812,0.0000513635,0.00007735972,0.00002548465,0.00002275478],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7133702,"threshold_uncertainty_score":0.8494837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05931482002999838,"score_gpt":0.3792455287670747,"score_spread":0.3199307087370763,"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."}}