{"id":"W3151806267","doi":"10.14288/1.0398233","title":"The Effectiveness of Image Augmentation in Deep Learning Networks for Detecting COVID-19 : A Geometric Transformation Perspective","year":2021,"lang":"en","type":"article","venue":"Repository for Publications and Research Data (ETH Zurich)","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia; Vancouver General Hospital; University of Manitoba","funders":"","keywords":"Overfitting; Deep learning; Artificial intelligence; Computer science; Transformation (genetics); Coronavirus disease 2019 (COVID-19); Machine learning; Training set; Artificial neural network; Image (mathematics); Geometric transformation; Big data; Pattern recognition (psychology); Data mining; Medicine","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008709492,0.00009772332,0.0002129496,0.0006429589,0.001164433,0.0002510459,0.0002460032,0.00009499641,0.0000024112],"category_scores_gemma":[0.02541668,0.00008076914,0.000062341,0.002197311,0.0001838729,0.0005362208,0.0001472047,0.0003677871,2.633522e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006628602,"about_ca_system_score_gemma":0.0007220058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004665551,"about_ca_topic_score_gemma":0.0001485962,"domain_scores_codex":[0.997526,0.0009153238,0.0003749727,0.0004820447,0.0003673467,0.0003342964],"domain_scores_gemma":[0.981396,0.01597083,0.0001334267,0.0006311152,0.001708131,0.0001604877],"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":[0.0171918,0.008006139,0.1003234,0.0383436,0.003160533,0.00007878718,0.03019095,0.03217661,0.2500708,0.100026,0.02376595,0.3966654],"study_design_scores_gemma":[0.01513077,0.002118757,0.1964283,0.0009789331,0.000519831,0.0002727241,0.03395149,0.5010054,0.04272686,0.003447428,0.2027202,0.0006993065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07343302,0.007252587,0.8830971,0.02842929,0.0001985926,0.006808415,0.0001536895,0.0001185539,0.0005087528],"genre_scores_gemma":[0.9941318,0.0007668883,0.0026536,0.00009813716,0.0001067282,0.001206802,0.0008651324,0.00002772923,0.0001432086],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9206988,"threshold_uncertainty_score":0.9827927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1007657677903278,"score_gpt":0.4510631997373535,"score_spread":0.3502974319470257,"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."}}