Enhancing Endoscopic Artefact Classification With GAN‐Based Synthetic Images Using Artefact Localisation Loss
Electronics Letters · 2026-01 · 62 (1)
DOI: 10.1049/ell2.70586 ↗At a glance
Journal article in Electronics Letters, published online on 2026-04-15. Written by Minhye Chang and 6 co-authors. 25 references. The full text is freely available (open access, CC BY-NC 4.0).
Abstract (original language)
Accurate artefact classification is essential for reliable diagnosis and computer‐aided analysis in endoscopy, as visual artefacts can severely degrade image quality. However, endoscopic artefact classification is often hindered by limited and imbalanced datasets. This letter introduces an artefact localisation loss (ALL) that guides StyleGAN2 with adaptive discriminator augmentation (StyleGAN2‐ADA) to focus on artefact regions, thereby improving the realism of synthetic images generated from small datasets. The synthetic images were then used for data augmentation, which significantly enhanced classification performance, particularly for underrepresented artefact classes. Experiments on in‐house and endoscopy artefact detection challenge (EAD2020) datasets achieved lower FID scores and showed consistent improvements in F1‐scores, demonstrating the effectiveness of the proposed ALL and synthetic augmentation for robust artefact classification.
Cite
APA
Chang, M., Bae, Y. M., Kang, D., Shin, K., Lee, W., Chung, H., & Ryu, J. K. (2026). Enhancing Endoscopic Artefact Classification With GAN‐Based Synthetic Images Using Artefact Localisation Loss. Electronics Letters, 62(1). https://doi.org/10.1049/ell2.70586
Vancouver
Chang M, Bae YM, Kang D, Shin K, Lee W, Chung H, et al. Enhancing Endoscopic Artefact Classification With GAN‐Based Synthetic Images Using Artefact Localisation Loss. Electronics Letters. 2026;62(1). doi:10.1049/ell2.70586
BibTeX
@article{Chang2026,
author = {Chang, Minhye and Bae, Young Min and Kang, Dong‐Goo and Shin, Kiyoung and Lee, Wonju and Chung, Hyunsoo and Ryu, Ji Kon},
title = {Enhancing Endoscopic Artefact Classification With GAN‐Based Synthetic Images Using Artefact Localisation Loss},
journal = {Electronics Letters},
year = {2026},
volume = {62},
number = {1},
doi = {10.1049/ell2.70586}
}
EUVIMED