{"id":"W1898227994","doi":"10.1109/crv.2015.25","title":"Lung Nodule Classification Using Deep Features in CT Images","year":2015,"lang":"en","type":"article","venue":"","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":377,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; National Cancer Institute; Foundation for the National Institutes of Health","keywords":"Lung cancer; CAD; Nodule (geology); Lung; Radiology; Computer-aided diagnosis; Artificial intelligence; Medicine; Cancer; Computer science; Lung cancer screening; Second opinion; Encoder; Pattern recognition (psychology); Medical physics; Pathology; Internal medicine; Engineering drawing","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":[0.00007736259,0.00006732243,0.0001169563,0.00005816603,0.00001500634,0.00001441839,0.00002417179,0.00002011421,0.00005625371],"category_scores_gemma":[0.00002623117,0.00004792394,0.00002700689,0.0001020821,0.00001479714,0.00006103309,0.00001136834,0.00005161323,0.00001847238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000430388,"about_ca_system_score_gemma":0.00006787053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006615861,"about_ca_topic_score_gemma":0.0002061341,"domain_scores_codex":[0.9995108,0.00001391625,0.00009623705,0.0001448054,0.000123986,0.0001102594],"domain_scores_gemma":[0.9996813,0.00001602213,0.00002409643,0.000152341,0.00004527158,0.00008098097],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006488657,0.0004115803,0.9652057,0.00005226319,0.00005647442,0.000101649,0.0003145262,0.00007303541,0.001284147,0.0007342072,0.02264321,0.009058276],"study_design_scores_gemma":[0.003045823,0.0001045013,0.9751714,0.0001222531,0.0001248803,0.00006809288,0.0005698274,0.005099691,0.01326028,0.0001220896,0.002189475,0.0001216774],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9555752,0.002666289,0.0003349382,0.00431823,0.0001875506,0.0003856854,0.000001971289,0.00005895396,0.03647122],"genre_scores_gemma":[0.9959956,0.00005747602,0.002779449,0.0002972932,0.00007915691,0.00002060503,0.00001406837,0.000009132055,0.0007472665],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04042039,"threshold_uncertainty_score":0.1954281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04352380629363663,"score_gpt":0.347446596619083,"score_spread":0.3039227903254464,"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."}}