{"id":"W2556626475","doi":"10.1016/j.eswa.2016.11.013","title":"Towards computer based lung disease diagnosis using accurate lung air segmentation of CT images in exhalation and inhalation phases","year":2016,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"National Institutes of Health","keywords":"Voxel; Thresholding; Segmentation; Computer science; Lung volumes; Lung; Volume (thermodynamics); COPD; Artificial intelligence; Biomedical engineering; Pattern recognition (psychology); Medicine; Image (mathematics); Physics","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":[0.00008131928,0.0001410376,0.0002255343,0.0001479009,0.00006537131,0.00001805462,0.00003269907,0.00002407105,0.00001541867],"category_scores_gemma":[0.000008540403,0.0000915062,0.00003265721,0.0002079455,0.0000489112,0.0002069362,0.00001228973,0.00002550524,9.978056e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003596833,"about_ca_system_score_gemma":0.0001126819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000420565,"about_ca_topic_score_gemma":0.00001594263,"domain_scores_codex":[0.9990386,0.00004384132,0.0003110586,0.0002866989,0.0001973645,0.0001224428],"domain_scores_gemma":[0.999248,0.0001106509,0.0001844726,0.0002352264,0.0001132232,0.0001084478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001287795,0.0005163422,0.9833624,0.0004066343,0.00008084551,0.000009955899,0.0002357353,0.001412734,0.003148696,0.0001506548,0.0006150224,0.009932138],"study_design_scores_gemma":[0.01035093,0.0002377445,0.8461612,0.004801861,0.0004672668,0.00003066865,0.0002359579,0.1063997,0.02990662,0.00002169858,0.0009242824,0.000462047],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7019066,0.002984405,0.2897687,0.001820602,0.00006049735,0.003236078,0.00009723293,0.00006135491,0.00006453836],"genre_scores_gemma":[0.9932232,0.0001803242,0.002808223,0.00006656424,0.0001120622,0.003490503,0.0000831177,0.00001923597,0.00001670371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2913167,"threshold_uncertainty_score":0.3731515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01884108499914931,"score_gpt":0.3215828325728669,"score_spread":0.3027417475737176,"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."}}