EUVIMEDSkopri EUVIMED
Crossref

Retinal vessel segmentation driven by structure prior tokens

Jiaqi Guo, Xinyu Guo, Quanyong Yi, Huaying Hao, Yitian Zhao

Medical Physics · 2025-08 · 52 (8)

DOI: 10.1002/mp.18018 ↗

At a glance

Journal article in Medical Physics, published online on 2025-09-03. Written by Jiaqi Guo and 4 co-authors. Institution: Laboratory of Advanced Theranostic Materials and Technology, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, N…. Major MEDLINE topics: Retinal Vessels, Image Processing, Computer-Assisted, Tomography, Optical Coherence. Cited 3 times so far (Crossref); 42 references. Funded by: National Key Research and Development Program of China, National Natural Science Foundation of China, Key Research and Development Program of Zhejiang Province.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Accurate retinal vessel segmentation from Optical Coherence Tomography Angiography (OCTA) images is vital in ophthalmic medicine, particularly for the early diagnosis and monitoring of diseases, such as diabetic retinopathy and hypertensive retinopathy. The retinal vascular system exhibits complex characteristics, including branching, crossing, and continuity, which are crucial for precise segmentation and subsequent medical analysis. However, traditional pixel‐wise vessel segmentation methods focus on learning how to effectively divide each pixel into different categories, relying mainly on local features, such as intensity and texture, and often neglecting the intrinsic structural properties of vessels. This can cause suboptimal segmentation accuracy and robustness, particularly when handling low‐contrast, noisy, or pathological images.

Purpose

This study aims to integrate structural priors into a segmentation framework. Prior embeddings are used to guide the segmentation process, which encode the typical morphology and topological structure of blood vessels. Incorporating these embeddings can improve the accuracy of retinal vessel segmentation, particularly in challenging areas such as small vessels and regions with ambiguous boundaries. This approach could help to preserve the integrity and continuity of the vascular structure, resulting in more reliable and precise segmentation.

Methods

This study adopts a generative image segmentation framework. A structured representation in a latent embedding space is presented to explore retinal vessel priors. On this basis, a prior‐driven retinal vessel segmentation network is introduced. First, the retinal vessel priors from ground truth data are learned, which are encoded as embedding tokens through a residual quantization reconstruction network. The learned priors are stored in a codebook. In our network, a raw OCTA image is transformed into semantic features using an encoder. Each semantic feature is subsequently represented by a set of embedding tokens from the codebook. Finally, the retinal vessels are reconstructed, preserving the integrity and continuity of the vascular structures using the learned structural priors.

Results

The performance of our proposed network was assessed across three OCTA datasets: publically available ROSE‐1 and ROSE‐2, and the private dataset OCTA‐Z. Both quantitative and qualitative evaluations revealed that our network outperformed current state‐of‐the‐art methods. In particular, our approach achieved the average Dice scores of 77.63, 71.01, and 81.11% for ROSE‐1, ROSE‐2, and OCTA‐Z, respectively.

Conclusions

The experimental results demonstrated that the proposed network effectively learned and utilized implicit vessel priors for OCTA vessel segmentation. Extensive evaluations indicated that our network surpassed the current state‐of‐the‐art methods. Specifically, our reconstruction approach of applying latent prior tokens offered a promising solution for the pattern representation of retinal vessels. In the future, we will extend this method to support more comprehensive retinal structure segmentation and eye‐related disease classification tasks. Additionally, we plan to integrate diverse and detailed prior knowledge, such as anatomical and pathological information, to enhance the performance and versatility of our approach.

Subjects

MeSH terms (MEDLINE)

Retinal VesselsImage Processing, Computer-AssistedTomography, Optical CoherenceHumans

Author keywords

optical coherence tomography angiographyresidual quantizationretinal vessel segmentation

Authors and institutions

  • Laboratory of Advanced Theranostic Materials and Technology, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China.
  • University of Chinese Academy of Sciences, Beijing, China.
  • Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, China.

Funding

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Key Research and Development Program of Zhejiang Province
  • Project of Ningbo Public Welfare Science and Technology
  • Ningbo 2025 S&T Mega project
  • Ningbo Clinical Research Center for Ophthalmology

Cite

APA

Guo, J., Guo, X., Yi, Q., Hao, H., & Zhao, Y. (2025). Retinal vessel segmentation driven by structure prior tokens. Medical Physics, 52(8). https://doi.org/10.1002/mp.18018

Vancouver

Guo J, Guo X, Yi Q, Hao H, Zhao Y. Retinal vessel segmentation driven by structure prior tokens. Medical Physics. 2025;52(8). doi:10.1002/mp.18018

BibTeX
@article{Guo2025,
  author = {Guo, Jiaqi and Guo, Xinyu and Yi, Quanyong and Hao, Huaying and Zhao, Yitian},
  title = {Retinal vessel segmentation driven by structure prior tokens},
  journal = {Medical Physics},
  year = {2025},
  volume = {52},
  number = {8},
  doi = {10.1002/mp.18018}
}
Start for free →