Article: Fundus image segmentation method based on improved DeepLabv3+ network Journal: International Journal of Wireless and Mobile Computing (IJWMC) 2025 Vol.28 No.4 pp.416 - 426 Abstract: Accurate optic disc (OD) and optic cup (OC) segmentation in fundus images is crucial for the automatic diagnosis and treatment of certain diseases. However, due to blurry boundaries and vessel occlusion in retinal fundus images, segmenting OD and OC remains a challenging task. This paper proposes an improved DeepLabv3+ network, which contains a novel sparse atrous spatial pyramid pooling (SparseASPP) module and an improved decoder architecture. Specifically, SparseASPP can enhance the ability of DeepLabv3+ to integrate multi-scale feature information, while the improved decoder architecture can effectively fuse low-resolution deep feature information to enhance the network's segmentation performance. The proposed method achieves significant improvements in segmentation accuracy on the RIGA+ dataset (including two training subsets and three test subsets) and the REFUGE dataset. These results demonstrate that our method outperforms DeepLabVv+ and other comparison methods. Inderscience Publishers - linking academia, business and industry through research

Title: Fundus image segmentation method based on improved DeepLabv3+ network

Authors: Liguo Zheng; Yingying Ge; Meili Zhu; Huican Li; Yanlin He; Caixia Zheng

Addresses: Jilin Animation Institute, Changchun City, Jilin Province, China ' Jilin Animation Institute, Changchun City, Jilin Province, China ' Jilin Animation Institute, Changchun City, Jilin Province, China ' College of Information Science and Technology, Northeast Normal University, Changchun, Jilin Province, China ' College of Information Science and Technology, Northeast Normal University, Changchun, Jilin Province, China ' College of Information Science and Technology, Northeast Normal University, Changchun, Jilin Province, China

Abstract: Accurate optic disc (OD) and optic cup (OC) segmentation in fundus images is crucial for the automatic diagnosis and treatment of certain diseases. However, due to blurry boundaries and vessel occlusion in retinal fundus images, segmenting OD and OC remains a challenging task. This paper proposes an improved DeepLabv3+ network, which contains a novel sparse atrous spatial pyramid pooling (SparseASPP) module and an improved decoder architecture. Specifically, SparseASPP can enhance the ability of DeepLabv3+ to integrate multi-scale feature information, while the improved decoder architecture can effectively fuse low-resolution deep feature information to enhance the network's segmentation performance. The proposed method achieves significant improvements in segmentation accuracy on the RIGA+ dataset (including two training subsets and three test subsets) and the REFUGE dataset. These results demonstrate that our method outperforms DeepLabVv+ and other comparison methods.

Keywords: deep learning; fundus images; optic cup and optic disc segmentation.

DOI: 10.1504/IJWMC.2025.146642

International Journal of Wireless and Mobile Computing, 2025 Vol.28 No.4, pp.416 - 426

Received: 10 May 2023
Accepted: 02 Sep 2023
Published online: 10 Jun 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Fundus image segmentation method based on improved DeepLabv3+ network

Keep up-to-date