{"id":"W4364356397","doi":"10.1016/j.compmedimag.2023.102232","title":"Semantically preserving adversarial unsupervised domain adaptation network for improving disease recognition from chest x-rays","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council; National Science Foundation; U.S. Department of Transportation; Amazon Web Services; Toyota USA; National Sleep Foundation","keywords":"Computer science; Artificial intelligence; Domain (mathematical analysis); Deep learning; Labeled data; Domain adaptation; Adaptation (eye); ENCODE; Pattern recognition (psychology); Adversarial system; Machine learning","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":[0.0009493328,0.0002381628,0.0004113757,0.000199467,0.000291533,0.000113703,0.0001594255,0.0001364649,0.00002483012],"category_scores_gemma":[0.001769225,0.0002323262,0.0001668543,0.0005285775,0.0002064099,0.0001548145,0.0002060583,0.0003270739,0.000007205745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003731448,"about_ca_system_score_gemma":0.000316535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000184885,"about_ca_topic_score_gemma":0.00001762093,"domain_scores_codex":[0.9977452,0.0001285154,0.0004408159,0.000608285,0.0005842868,0.0004928641],"domain_scores_gemma":[0.9969499,0.001742529,0.0001032618,0.0003090226,0.0001806648,0.0007146482],"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":[0.00613605,0.001175048,0.05540356,0.006171673,0.0007711857,0.001881118,0.004353516,0.0006480308,0.007402808,0.001322742,0.05382713,0.8609071],"study_design_scores_gemma":[0.006714697,0.00007967479,0.05233569,0.001393759,0.0003449764,0.000007579338,0.0001002456,0.9177557,0.00001633225,0.01199907,0.008955743,0.0002965833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3882447,0.0005874683,0.52553,0.08170351,0.001740536,0.001184799,0.0001052152,0.0008946724,0.000009013751],"genre_scores_gemma":[0.8040774,0.001130912,0.1318226,0.05049846,0.007378772,0.0003682571,0.004488513,0.0002052482,0.00002984448],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9171076,"threshold_uncertainty_score":0.9473988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0339811903640427,"score_gpt":0.2922418661788528,"score_spread":0.2582606758148102,"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."}}