{"id":"W2774301822","doi":"10.1109/icassp.2018.8461430","title":"Generalization of Deep Neural Networks for Chest Pathology Classification in X-Rays Using Generative Adversarial Networks","year":2018,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; University of Toronto","funders":"","keywords":"Convolutional neural network; Generative adversarial network; Artificial intelligence; Computer science; Generalization; Deep learning; Image (mathematics); Adversarial system; Representation (politics); Generative grammar; Pattern recognition (psychology); Artificial neural network; Contextual image classification; Machine learning; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001119833,0.0007742945,0.0004404402,0.0004403107,0.000184144,0.0004974484,0.0008913981,0.0007096325,0.001044966],"category_scores_gemma":[0.002712237,0.0003686663,0.0006194026,0.0002935365,0.0006522972,0.0005685079,0.001003163,0.001294256,0.0002791478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009568234,"about_ca_system_score_gemma":0.0005044473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004195937,"about_ca_topic_score_gemma":0.004860173,"domain_scores_codex":[0.9997087,0.00009282776,0.00001248138,0.00008608349,0.00006157239,0.00003818621],"domain_scores_gemma":[0.9991205,0.0004996779,0.00009827509,0.0001211397,0.0001144083,0.00004591136],"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":[0.00006515037,0.00003872232,0.001864835,0.00002219443,0.00002917984,0.00005018395,0.00002908676,0.9667374,0.002518949,0.002230229,0.0008704271,0.02554352],"study_design_scores_gemma":[0.00000178296,0.000007049275,0.000166086,0.000002277013,0.000001829162,0.000008740695,0.000001640259,0.9982309,0.0004687304,0.00103382,0.00007559931,0.000001635938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1721258,0.0005671481,0.8218615,0.0008108201,0.00008831963,0.00007992524,0.0002961429,0.001322537,0.002847896],"genre_scores_gemma":[0.9385948,0.0001982702,0.05771505,0.0002512645,0.00004043526,0.00007714346,0.0005078295,0.00006703829,0.002548303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004195937,"threshold_uncertainty_score":0.008342981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05417084265732602,"score_gpt":0.2980515653299317,"score_spread":0.2438807226726057,"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."}}