{"id":"W4319001820","doi":"10.1016/j.bea.2023.100076","title":"Applications of deep learning in disease diagnosis of chest radiographs: A survey on materials and methods","year":2023,"lang":"en","type":"article","venue":"Biomedical Engineering Advances","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"Deep learning; Convolutional neural network; Artificial intelligence; Computer science; Medical imaging; Modalities; Positron emission tomography; Machine learning; Radiology; Radiography; Magnetic resonance imaging; Transfer of learning; Medical physics; Medicine","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":[0.000882185,0.0001160055,0.0003774466,0.0006276905,0.00001645489,0.000004793516,0.00007346823,0.00005890695,0.00001665862],"category_scores_gemma":[0.002714864,0.0001063043,0.00004279951,0.001376046,0.0001329545,0.0000358785,0.00004083269,0.0001058313,0.00000166675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002679433,"about_ca_system_score_gemma":0.00003064114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000101947,"about_ca_topic_score_gemma":0.00000473509,"domain_scores_codex":[0.9989534,0.00008435327,0.0003394752,0.0002281189,0.0002177109,0.000176913],"domain_scores_gemma":[0.9974812,0.002064467,0.0000783876,0.0001663631,0.00003442638,0.0001751148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003215796,0.0009332667,0.3392068,0.006446743,0.000157822,0.00005452739,0.0006133012,0.009416211,0.04050275,0.0001922879,0.0002426537,0.601912],"study_design_scores_gemma":[0.0006903035,0.0001640398,0.9398867,0.0007374504,0.00004666691,9.753727e-7,0.00002851999,0.003861981,0.007372497,0.000039287,0.04703428,0.0001372277],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9646226,0.00647923,0.02414186,0.00320171,0.0002866033,0.0007951008,0.0001284288,0.0003408126,0.000003722052],"genre_scores_gemma":[0.9874504,0.003553923,0.008389372,0.0000929341,0.00005612012,0.0003208227,0.0001030046,0.00002742677,0.000005990865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6017748,"threshold_uncertainty_score":0.4334964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01812260851237345,"score_gpt":0.3503338233097634,"score_spread":0.3322112147973899,"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."}}