An Accurate and Efficient Neural Network for OCTA Vessel Segmentation and a New Dataset

Haojian Ning, Chengliang Wang, Xinrun Chen, Shiying Li
9/18/2023
eess.IVcs.CV

Official code: nhjydywd/OCTA-FRNet (34 stars, MIT, last commit 2024-01-09).

Abstract

Optical coherence tomography angiography (OCTA) is a noninvasive imaging technique that can reveal high-resolution retinal vessels. In this work, we propose an accurate and efficient neural network for retinal vessel segmentation in OCTA images. The proposed network achieves accuracy comparable to other SOTA methods, while having fewer parameters and faster inference speed (e.g. 110x lighter and 1.3x faster than U-Net), which is very friendly for industrial applications. This is achieved by applying the modified Recurrent ConvNeXt Block to a full resolution convolutional network. In addition, we create a new dataset containing 918 OCTA images and their corresponding vessel annotations. The data set is semi-automatically annotated with the help of Segment Anything Model (SAM), which greatly improves the annotation speed. For the benefit of the community, our code and dataset can be obtained from https://github.com/nhjydywd/OCTA-FRNet.

View on arXivView PDF

Code Implementations(1)

nhjydywd/OCTA-FRNetOfficial100%
MIT
342PythonSep 6, 20232 years agoMIT

Similar Papers

Synthetic optical coherence tomography angiographs for detailed retinal vessel segmentation without human annotations

90% match1 repo512023

DB-KAUNet: An Adaptive Dual Branch Kolmogorov-Arnold UNet for Retinal Vessel Segmentation

89% match2025

FS-Net: Full Scale Network and Adaptive Threshold for Improving Extraction of Micro-Retinal Vessel Structures

89% match2023

Augmentation is AUtO-Net: Augmentation-Driven Contrastive Multiview Learning for Medical Image Segmentation

88% match2023

Segmentation of Retinal Blood Vessels Using Deep Learning

87% match2023

Retinal Vessel Segmentation based on Fully Convolutional Networks

87% match1 repo502019

Cite this paper

@article{ning2023accurate,
  title  = {An Accurate and Efficient Neural Network for OCTA Vessel Segmentation and a New Dataset},
  author = {Haojian Ning and Chengliang Wang and Xinrun Chen and Shiying Li},
  year   = {2023},
  eprint = {2309.09483},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.09483v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.09483.svg)](https://codeofpaper.com/paper/2309.09483)

Discussion