000153698 001__ 153698
000153698 005__ 20251017144641.0
000153698 0247_ $$2doi$$a10.1038/s41598-025-95390-3
000153698 0248_ $$2sideral$$a143766
000153698 037__ $$aART-2025-143766
000153698 041__ $$aeng
000153698 100__ $$aMusa, Aminu
000153698 245__ $$aAddressing cross-population domain shift in chest X-ray classification through supervised adversarial domain adaptation
000153698 260__ $$c2025
000153698 5060_ $$aAccess copy available to the general public$$fUnrestricted
000153698 5203_ $$aMedical image analysis, empowered by artificial intelligence (AI), plays a crucial role in modern healthcare diagnostics. However, the effectiveness of machine learning models hinges on their ability to generalize to diverse patient populations, presenting domain shift challenges. This study explores the domain shift problem in chest X-ray classification, focusing on cross-population variations, especially in underrepresented groups. We analyze the impact of domain shifts across three population datasets acting as sources using a Nigerian chest X-ray dataset acting as the target. Model performance is evaluated to assess disparities between source and target populations, revealing large discrepancies when the models trained on a source were applied to the target domain. To address with the evident domain shift among the populations, we propose a supervised adversarial domain adaptation (ADA) technique. The feature extractor is first trained on the source domain using a supervised loss function in ADA. The feature extractor is then frozen, and an adversarial domain discriminator is introduced to distinguish between the source and target domains. Adversarial training fine-tunes the feature extractor, making features from both domains indistinguishable, thereby creating domain-invariant features. The technique was evaluated on the Nigerian dataset, showing significant improvements in chest X-ray classification performance. The proposed model achieved a 90.08% accuracy and a 96% AUC score, outperforming existing approaches such as multi-task learning (MTL) and continual learning (CL). This research highlights the importance of developing domain-aware models in AI-driven healthcare, offering a solution to cross-population domain shift challenges in medical imaging.
000153698 536__ $$9info:eu-repo/grantAgreement/ES/DGA/B50-24$$9info:eu-repo/grantAgreement/ES/DGA/T64-23R$$9info:eu-repo/grantAgreement/ES/MICINN/PID2022-138703OB-I00
000153698 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttps://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
000153698 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000153698 700__ $$aPrasad, Rajesh
000153698 700__ $$0(orcid)0000-0003-1270-5852$$aHernández, Mónica$$uUniversidad de Zaragoza
000153698 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf.
000153698 773__ $$g15, 1 (2025), 11383 [13 pp.]$$pSci. rep. (Nat. Publ. Group)$$tScientific reports (Nature Publishing Group)$$x2045-2322
000153698 8564_ $$s1897512$$uhttps://zaguan.unizar.es/record/153698/files/texto_completo.pdf$$yVersión publicada
000153698 8564_ $$s2582520$$uhttps://zaguan.unizar.es/record/153698/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000153698 909CO $$ooai:zaguan.unizar.es:153698$$particulos$$pdriver
000153698 951__ $$a2025-10-17-14:32:11
000153698 980__ $$aARTICLE