{
  "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.",
  "abstract_shown": true,
  "affiliations": [
    "School of Ophthalmology & Optometry, Wenzhou Medical University, Wenzhou 325000, China.",
    "School of Data Science and Artificial Intelligence, Wenzhou University of Technology, Wenzhou 325000, China."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Xudong Wang",
      "orcid": "0009-0003-0256-554X"
    },
    {
      "affs": [
        1
      ],
      "name": "Qinghong Gao",
      "orcid": "0009-0007-2314-839X"
    },
    {
      "affs": [
        0
      ],
      "name": "Ran Yang"
    },
    {
      "affs": [
        0
      ],
      "name": "Xuelian Yang"
    },
    {
      "affs": [
        1
      ],
      "name": "Rui Yao",
      "orcid": "0009-0004-1736-2937"
    },
    {
      "affs": [
        1
      ],
      "name": "Shu'an Liu",
      "orcid": "0000-0002-5618-5169"
    },
    {
      "affs": [
        1
      ],
      "name": "Maosong Jiang"
    },
    {
      "affs": [
        1
      ],
      "name": "Caiye Fan",
      "orcid": "0009-0004-3096-2013"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Zuoping Tan"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Yuanyuan Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3j8bqcywnz30e.bib",
  "cited_by": 0,
  "doi": "10.3390/bioengineering13101147",
  "fulltext_url": "https://europepmc.org/articles/PMC13701182",
  "id": "3j8bqcywnz30e",
  "issns": [
    "2306-5354"
  ],
  "landing_url": "https://europepmc.org/article/MED/42939002",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2741|Retinal Imaging and Analysis"
    ]
  ],
  "openalex": "W7214981868",
  "pdf_url": "https://europepmc.org/articles/PMC13701182?pdf=render",
  "pmcid": "PMC13701182",
  "pmid": "42939002",
  "published": "2026-09-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3j8bqcywnz30e.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:22:24Z",
      "native_id": "MED:42939002",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42939002"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2741|Retinal Imaging and Analysis",
      "subfield": "imaging"
    }
  ],
  "title": "RCNet: A Hybrid Network Adapted for OCTA Retinal Capillary Segmentation.",
  "title_text": "RCNet: A Hybrid Network Adapted for OCTA Retinal Capillary Segmentation.",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:22:24Z",
  "url": "https://research.draconitic.com/paper/3j8bqcywnz30e",
  "venue": "Bioengineering (Basel, Switzerland)",
  "versions": []
}