EUVIMEDEUVIMED entdecken
Crossref

Points-Supervised Fundus Vessel Segmentation via Shape Priors and Contrastive Learning

Kaiwen Li, Hangzhou He, Shuang Zeng, Xinliang Zhang, Yuanwei Li, Lei Zhu, Yanye Lu

IEEE Transactions on Medical Imaging · 2025

DOI: 10.1109/tmi.2025.3586692 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025. Verfasst von Kaiwen Li und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Retinal Vessels, Fundus Oculi, Supervised Machine Learning, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science Foundation of Peking University Cancer Hospital, China National Postdoctoral Program for Innovative Talents.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The performance of fully supervised methods for fundus vessel segmentation highly relies on a large number of full labels which are laborious and time-consuming to obtain. Although weak annotations relax the requirement for pixel-wise labeling, they pose challenges in learning comprehensive information about the target. Some methods use pseudo labels generated from network predictions for extra supervision, but false positive predictions in these labels may harm training. In this paper, to tackle this problem and to balance the annotation cost and supervision information, we introduce point annotations to fundus vessel segmentation and propose a novel method, called Points-based Vessel segmentation Network (PVN), to enhance the segmentation accuracy. In PVN, to avoid noise in pseudo labels, by combining proposed Point Activation Maps, shape priors of vessels are learned and used as soft supervision. Additionally, to further leverage the annotated vessel and background points, we design a novel contrastive learning method in a pixels-and-regions-mixed manner, which helps learn discriminative features by distinguishing between pixel and region samples of vessels and background. The performance of PVN is evaluated on laser speckle contrast imaging fundus images, 548 nm fundus images, and three public datasets, where PVN outperforms other point-supervised methods. Even with only 1% annotated pixels, PVN still achieves excellent performance. Our method is also flexible and easy to be combined with other frameworks. To the best of our knowledge, we are the first to propose and demonstrate the effectiveness of point annotations for fundus vessel segmentation. Our code is available at: https://github.com/kaiwenli325/PVN.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Retinal VesselsFundus OculiSupervised Machine LearningImage Interpretation, Computer-AssistedImage Processing, Computer-AssistedHumansAlgorithmsDatabases, Factual

Förderung

  • National Natural Science Foundation of China
  • Science Foundation of Peking University Cancer Hospital
  • China National Postdoctoral Program for Innovative Talents
  • Clinical Medicine Plus X–Young Scholars Project of Peking University
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Li, K., He, H., Zeng, S., Zhang, X., Li, Y., Zhu, L., & Lu, Y. (2025). Points-Supervised Fundus Vessel Segmentation via Shape Priors and Contrastive Learning. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2025.3586692

Vancouver

Li K, He H, Zeng S, Zhang X, Li Y, Zhu L, et al. Points-Supervised Fundus Vessel Segmentation via Shape Priors and Contrastive Learning. IEEE Transactions on Medical Imaging. 2025. doi:10.1109/tmi.2025.3586692

BibTeX
@article{Li2025,
  author = {Li, Kaiwen and He, Hangzhou and Zeng, Shuang and Zhang, Xinliang and Li, Yuanwei and Zhu, Lei and Lu, Yanye},
  title = {Points-Supervised Fundus Vessel Segmentation via Shape Priors and Contrastive Learning},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2025},
  doi = {10.1109/tmi.2025.3586692}
}
Kostenlos starten →