Uncertainty‐guided cross‐level fusion network for retinal OCT image segmentation
Medical Physics · 2025
DOI: 10.1002/mp.18102 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, 2025. Verfasst von Jiaxin Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: MIPAV Lab, School of Electronics and Information Engineering, Soochow University, Suzhou, China. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Retina, Image Processing, Computer-Assisted, Neural Networks, Computer. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
Background
Deep learning‐based segmentation methods for optical coherence tomography (OCT) have demonstrated outstanding performance. However, the stochastic distribution of training data and the inherent limitations of deep neural networks introduce uncertainty into the segmentation process. Accurately estimating this uncertainty is essential for generating reliable confidence assessments and improving model predictions.
Purpose
To address these challenges, we propose a novel uncertainty‐guided cross‐layer fusion network (UGCFNet) for retinal OCT segmentation. UGCFNet integrates uncertainty quantification into the training process of deep neural networks and leverages this uncertainty to enhance segmentation accuracy.
Methods
Our model employs an encoder–decoder architecture that quantitatively assesses uncertainty at multiple stages, directing the network's focus toward regions with higher uncertainty. By facilitating cross‐layer feature fusion, UGCFNet enhances the comprehensive understanding of both semantic information and morphological details. Additionally, we incorporate an improved Bayesian neural network loss function alongside an uncertainty‐aware loss function, enabling the network to effectively utilize these mechanisms for better uncertainty modeling.
Results
We conducted extensive experiments on the publicly available AI‐Challenger and OIMHS OCT segmentation datasets. The training, validation, and testing sets of the AI‐Challenger dataset are comprised of 32, 8, and 43 OCT volumes, yielding a total of 4096, 1024, and 5504 B‐scans, respectively. The training, validation, and testing sets of the OIMHS dataset consist of 100, 25, and 25 OCT volumes, resulting in 2,310, 798, and 751 B‐scans, respectively. The results demonstrate that UGCFNet achieves state‐of‐the‐art performance, with average Dice similarity coefficients of 79.47% and 93.22% on the respective datasets.
Conclusion
Our proposed UGCFNet significantly advances retinal OCT segmentation by integrating uncertainty guidance and cross‐level feature fusion, offering more reliable and accurate segmentation outcomes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- MIPAV Lab, School of Electronics and Information Engineering, Soochow University, Suzhou, China.
- The State Key Laboratory of Radiation Medicine and Protection, Soochow University, Suzhou, China.
- School of Future Science and Engineering, Soochow University, Suzhou, China.
- Department of Ophthalmology, Shanghai Tenth People's Hospital, Tongji University School of Medicine, Shanghai, China.
- The Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province
- China Postdoctoral Science Foundation
- Natural Science Foundation of the Jiangsu Higher Education Institutions of China
Zitieren
APA
Wang, J., Zhu, W., Xiang, D., Chen, X., Peng, T., Peng, Q., Wang, M., & Shi, F. (2025). Uncertainty‐guided cross‐level fusion network for retinal OCT image segmentation. Medical Physics. https://doi.org/10.1002/mp.18102
Vancouver
Wang J, Zhu W, Xiang D, Chen X, Peng T, Peng Q, et al. Uncertainty‐guided cross‐level fusion network for retinal OCT image segmentation. Medical Physics. 2025. doi:10.1002/mp.18102
BibTeX
@article{Wang2025,
author = {Wang, Jiaxin and Zhu, Weifang and Xiang, Dehui and Chen, Xinjian and Peng, Tao and Peng, Qing and Wang, Meng and Shi, Fei},
title = {Uncertainty‐guided cross‐level fusion network for retinal OCT image segmentation},
journal = {Medical Physics},
year = {2025},
doi = {10.1002/mp.18102}
}
EUVIMED