Image quality improvement of liver ultrasound using unsupervised deep learning
PLOS One · 28.04.2026 · 21 (4) · e0348137
DOI: 10.1371/journal.pone.0348137 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 28.04.2026. Verfasst von Jaeyoung Huh und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea. Hauptthemen laut MEDLINE: Deep Learning, Liver, Unsupervised Machine Learning, Liver Cirrhosis. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Chronic liver disease (CLD) and subsequent liver cirrhosis (LC) are common causes of death and healthcare-related socio-economical costs worldwide. Ultrasound (US) is the first-line imaging modality for assessing the liver and associated hepatocellular carcinomas. Poor quality liver US images caused by aging or inadequate management of US equipment, can pose significant challenges in both diagnosis and treatment. From this perspective, the aim of this study was to enhance and assess the image quality of liver US obtained from an older, lower-performing device using a deep learning approach. A neural network based on a switchable cycle generative adversarial network (CycleGAN) was trained in an unsupervised learning setting, with low-quality images as inputs and high-quality images as targets. The study included consecutively acquired grey-scale liver US examinations from both a 12-year-old and a 4-year-old US device. Images from the older device served as inputs, while images from the newer device were used as targets for the deep learning-based algorithm. Image quality was evaluated by two experienced reviewers. The algorithm significantly improved the brightness, contrast, and overall quality of the reconstructed liver US images (p < 0.001), as assessed by both reviewers. However, no significant differences in image resolution and reverberation artifacts were noted by one of the reviewers. The weighted kappa values for image quality and diagnostic performance ranged from 0.225 to 0.838, indicating fair to almost-perfect inter-reader agreement. The proposed algorithm effectively enhances low-quality liver US images to high diagnostic quality, thereby potentially supporting clinical assessment and intervention in patients with LC.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea.
- Department of Radiology, Chung-Ang University Hospital, Seoul, South Korea.
- Chung-Ang University, College of Medicine, Seoul, South Korea.
- Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea.
- Department of Radiology, Chungnam National University Hospital, Chungnam National University College of Medicine, Daejeon, South Korea.
ORCID-Profile: Jaeyoung Huh, Eun Sun Lee, Jeong Eun Lee
Zitieren
APA
Huh, J., Choi, J. H., Lee, E. S., Ye, J. C., Lee, J. E., Park, H. J., & Choi, B. I. (2026). Image quality improvement of liver ultrasound using unsupervised deep learning. PLOS One, 21(4), e0348137. https://doi.org/10.1371/journal.pone.0348137
Vancouver
Huh J, Choi JH, Lee ES, Ye JC, Lee JE, Park HJ, et al. Image quality improvement of liver ultrasound using unsupervised deep learning. PLOS One. 2026;21(4):e0348137. doi:10.1371/journal.pone.0348137
BibTeX
@article{Huh2026,
author = {Huh, Jaeyoung and Choi, Joo Hyeok and Lee, Eun Sun and Ye, Jong Chul and Lee, Jeong Eun and Park, Hyun Jeong and Choi, Byung Ihn},
title = {Image quality improvement of liver ultrasound using unsupervised deep learning},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {4},
pages = {e0348137},
doi = {10.1371/journal.pone.0348137}
}
EUVIMED