{"id":"W4399526820","doi":"10.1109/access.2024.3412608","title":"Toward Improved Interpretability in Medical Imaging: Revealing the Disease Evidence From Chest X-Ray Images Using an Adversarial Generative Approach","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Toyota Foundation; Canada Research Chairs; Japan Science and Technology Agency; China Scholarship Council; U.S. Department of Transportation; National Science Foundation","keywords":"Interpretability; Adversarial system; Medical imaging; Computer science; Artificial intelligence; Generative grammar; Computer vision; Pattern recognition (psychology); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002227933,0.001101056,0.0008490268,0.001088181,0.0002410755,0.001316459,0.00107977,0.00139811,0.001619867],"category_scores_gemma":[0.006810202,0.0006555555,0.001422433,0.0003978488,0.001323572,0.001089392,0.001666821,0.00224184,0.0003860204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007839384,"about_ca_system_score_gemma":0.0005591108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001806689,"about_ca_topic_score_gemma":0.001796578,"domain_scores_codex":[0.9991474,0.000357055,0.00004893765,0.0001904628,0.0001850749,0.00007098168],"domain_scores_gemma":[0.9965143,0.002479706,0.0003208542,0.0003313317,0.0002392059,0.0001145678],"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":[0.0004642036,0.00008514305,0.004077214,0.0002050747,0.0001387033,0.0006690333,0.0002635976,0.7917791,0.01602403,0.01186392,0.002541237,0.1718888],"study_design_scores_gemma":[0.000008543212,0.00002996007,0.0003898724,0.00001955117,0.00001837898,0.0001265886,0.00001049453,0.9909115,0.002225654,0.005798358,0.0004535522,0.000007549747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03771546,0.0007255183,0.9584545,0.0009567681,0.00006802023,0.00005995395,0.0001479415,0.0006494725,0.001222264],"genre_scores_gemma":[0.7889593,0.001103088,0.2040792,0.0008873904,0.0002552573,0.0001013823,0.0006743998,0.0002474834,0.003692567],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002227933,"threshold_uncertainty_score":0.01178259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1041890096479188,"score_gpt":0.4086844351355929,"score_spread":0.3044954254876741,"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."}}