A Mixture of Experts (MoE) and Transfer Learning Combined Model for Pneumonia Detection in X-Ray Images
DS Journal of Multidisciplinary · 31.03.2026 · 3 (1) · 17-24
DOI: 10.59232/dsm-v3i1p102 ↗Kurz gefasst
Fachartikel in der Zeitschrift DS Journal of Multidisciplinary, online erschienen am 31.03.2026. Verfasst von Hoang Trinh und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Detecting pneumonia from chest X-ray images is a critical and challenging task due to the diverse and sometimes subtle manifestations of lesions. This paper proposes a fusion model that combines a Mixture of Experts (MoE) architecture with Transfer Learning techniques to improve the accuracy and robustness of the diagnostic system. The model consists of local experts, which are trained specifically on the left and right lung regions after a segmentation step, and a global expert that processes the entire image. Each expert is built upon pre-trained Convolutional Neural Network (CNN) architectures and subsequently fine-tuned on X-ray data. Tests on the PneumoniaMNIST dataset reveal that the suggested model might greatly enhance accuracy and recall compared to baseline methods. This opens up new possibilities for automated medical diagnostic support systems.
Zitieren
APA
Trinh, H., Nguyen, T., & Tran, H. (2026). A Mixture of Experts (MoE) and Transfer Learning Combined Model for Pneumonia Detection in X-Ray Images. DS Journal of Multidisciplinary, 3(1), 17-24. https://doi.org/10.59232/dsm-v3i1p102
Vancouver
Trinh H, Nguyen T, Tran H. A Mixture of Experts (MoE) and Transfer Learning Combined Model for Pneumonia Detection in X-Ray Images. DS Journal of Multidisciplinary. 2026;3(1):17-24. doi:10.59232/dsm-v3i1p102
BibTeX
@article{Trinh2026,
author = {Trinh, Hoang and Nguyen, Thao and Tran, Hai},
title = {A Mixture of Experts (MoE) and Transfer Learning Combined Model for Pneumonia Detection in X-Ray Images},
journal = {DS Journal of Multidisciplinary},
year = {2026},
volume = {3},
number = {1},
pages = {17--24},
doi = {10.59232/dsm-v3i1p102}
}
EUVIMED