Next Article in Journal
Gravitation with Cosmological Term, Expansion of the Universe as Uniform Acceleration in Clifford Coordinates
Next Article in Special Issue
Principal Component Wavelet Networks for Solving Linear Inverse Problems
Previous Article in Journal
Optimization Model for the Pavement Pothole Repair Problem Considering Consumable Resources
Previous Article in Special Issue
An Improved Local Search Genetic Algorithm with a New Mapped Adaptive Operator Applied to Pseudo-Coloring Problem
Article

Multi-Scale and Multi-Branch Convolutional Neural Network for Retinal Image Segmentation

by , *,†, and
College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editor: Bernard Tiddeman
Symmetry 2021, 13(3), 365; https://doi.org/10.3390/sym13030365
Received: 6 January 2021 / Revised: 15 February 2021 / Accepted: 19 February 2021 / Published: 24 February 2021
(This article belongs to the Special Issue Symmetry in Vision II)
The accurate segmentation of retinal images is a basic step in screening for retinopathy and glaucoma. Most existing retinal image segmentation methods have insufficient feature information extraction. They are susceptible to the impact of the lesion area and poor image quality, resulting in the poor recovery of contextual information. This also causes the segmentation results of the model to be noisy and low in accuracy. Therefore, this paper proposes a multi-scale and multi-branch convolutional neural network model (multi-scale and multi-branch network (MSMB-Net)) for retinal image segmentation. The model uses atrous convolution with different expansion rates and skip connections to reduce the loss of feature information. Receiving domains of different sizes captures global context information. The model fully integrates shallow and deep semantic information and retains rich spatial information. The network embeds an improved attention mechanism to obtain more detailed information, which can improve the accuracy of segmentation. Finally, the method of this paper was validated on the fundus vascular datasets, DRIVE, STARE and CHASE datasets, with accuracies/F1 of 0.9708/0.8320, 0.9753/0.8469 and 0.9767/0.8190, respectively. The effectiveness of the method in this paper was further validated on the optic disc visual cup DRISHTI-GS1 dataset with an accuracy/F1 of 0.9985/0.9770. Experimental results show that, compared with existing retinal image segmentation methods, our proposed method has good segmentation performance in all four benchmark tests. View Full-Text
Keywords: retinal image segmentation; convolutional neural network; deep learning retinal image segmentation; convolutional neural network; deep learning
Show Figures

Figure 1

MDPI and ACS Style

Jiang, Y.; Liu, W.; Wu, C.; Yao, H. Multi-Scale and Multi-Branch Convolutional Neural Network for Retinal Image Segmentation. Symmetry 2021, 13, 365. https://doi.org/10.3390/sym13030365

AMA Style

Jiang Y, Liu W, Wu C, Yao H. Multi-Scale and Multi-Branch Convolutional Neural Network for Retinal Image Segmentation. Symmetry. 2021; 13(3):365. https://doi.org/10.3390/sym13030365

Chicago/Turabian Style

Jiang, Yun, Wenhuan Liu, Chao Wu, and Huixiao Yao. 2021. "Multi-Scale and Multi-Branch Convolutional Neural Network for Retinal Image Segmentation" Symmetry 13, no. 3: 365. https://doi.org/10.3390/sym13030365

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop