RCNet: A Hybrid Network Adapted for OCTA Retinal Capillary Segmentation.
- 1School of Ophthalmology & Optometry, Wenzhou Medical University, Wenzhou 325000, China.
- 2School of Data Science and Artificial Intelligence, Wenzhou University of Technology, Wenzhou 325000, China.
Abstract
Optical Coherence Tomography Angiography (OCTA) provides clear visualization of ocular microvascular details, serving as a critical tool for assessing retinal and choroidal vascular systems. However, the complex capillary structure and low capillary-to-background contrast in high-resolution OCTA images pose significant challenges for segmentation. To address the low segmentation accuracy of traditional methods, this paper proposes RCNet, a hybrid CNN-Transformer network. RCNet adopts an encoder-decoder architecture based on Bi-Level Routing Attention (BRA), where bi-level routing attention focuses on densely vascularized regions, optimizing global capillary feature extraction. A Convolutional Bottleneck Module (CBM) splits bottleneck features into two channel groups using a fixed ratio α. A high-capacity branch enhances local details, while a lightweight branch preserves complementary information. The branches are then fused. Additionally, a Dense Skip Connection Module (DSCM) enhances feature information flow in low-contrast regions, compensating for spatial information loss. By integrating CNN's local feature extraction with Transformer's global dependency modeling, RCNet achieves accurate segmentation of OCTA capillary images. Experiments on the OCTA-500 and ROSE datasets demonstrate that RCNet achieved a higher point estimate under the current protocol, facilitating and assisting in the clinical assessment of ocular diseases.
Related
- Hybrid feature pyramid attention and capsule network (FpaNet+CapsNet) for enhanced spatial and contextual feature extraction for improved brain tumor segmentation
- Retinal Capillary Loss Is More Severe in the Midperiphery Than in the Macula in Eyes With Diabetic Retinopathy Compared to Healthy Eyes
- Automated Segmentation of Retinal Pigment Epithelium Layers in High-Resolution OCT
- Evaluating the real-world accessibility of open-source deep learning models for retinal vessel segmentation in optical coherence tomography angiography
- Retinal vessel segmentation using Kolmogorov-Arnold networks and test-time adaptation
BibTeX
@article{wang2026rcnet,
title = {{RCNet: A Hybrid Network Adapted for OCTA Retinal Capillary Segmentation.}},
author = {Xudong Wang and Qinghong Gao and Ran Yang and Xuelian Yang and Rui Yao and Shu'an Liu and Maosong Jiang and Caiye Fan and Zuoping Tan and Yuanyuan Wang},
journal = {Bioengineering (Basel, Switzerland)},
year = {2026},
month = sep,
doi = {10.3390/bioengineering13101147},
url = {https://europepmc.org/article/MED/42939002},
note = {CC BY},
}
RIS
TY - JOUR
TI - RCNet: A Hybrid Network Adapted for OCTA Retinal Capillary Segmentation.
AU - Xudong Wang
AU - Qinghong Gao
AU - Ran Yang
AU - Xuelian Yang
AU - Rui Yao
AU - Shu'an Liu
AU - Maosong Jiang
AU - Caiye Fan
AU - Zuoping Tan
AU - Yuanyuan Wang
PY - 2026
DA - 2026/09/30
JO - Bioengineering (Basel, Switzerland)
DO - 10.3390/bioengineering13101147
UR - https://europepmc.org/article/MED/42939002
AB - Optical Coherence Tomography Angiography (OCTA) provides clear visualization of ocular microvascular details, serving as a critical tool for assessing retinal and choroidal vascular systems. However, the complex capillary structure and low capillary-to-background contrast in high-resolution OCTA images pose significant challenges for segmentation. To address the low segmentation accuracy of traditional methods, this paper proposes RCNet, a hybrid CNN-Transformer network. RCNet adopts an encoder-decoder architecture based on Bi-Level Routing Attention (BRA), where bi-level routing attention focuses on densely vascularized regions, optimizing global capillary feature extraction. A Convolutional Bottleneck Module (CBM) splits bottleneck features into two channel groups using a fixed ratio α. A high-capacity branch enhances local details, while a lightweight branch preserves complementary information. The branches are then fused. Additionally, a Dense Skip Connection Module (DSCM) enhances feature information flow in low-contrast regions, compensating for spatial information loss. By integrating CNN's local feature extraction with Transformer's global dependency modeling, RCNet achieves accurate segmentation of OCTA capillary images. Experiments on the OCTA-500 and ROSE datasets demonstrate that RCNet achieved a higher point estimate under the current protocol, facilitating and assisting in the clinical assessment of ocular diseases.
SN - 2306-5354
ER -