EARDS: EfficientNet and attention-based residual depth-wise separable convolution for joint OD and OC segmentation

• Published in: Frontiers in neuroscience Vol. 17; p. 1139181
• Main Authors: Zhou, Wei, Ji, Jianhang, Jiang, Yan, Wang, Jing, Qi, Qi, Yi, Yugen
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 09.03.2023; Frontiers Media S.A
• Subjects: Accuracy; attention; Blood vessels; Classification; Computer applications; Deep learning; EfficientNet; Glaucoma; joint optic disc and cup segmentation; Machine learning; Neuroscience; residual depth-wise separable convolution; Sampling techniques; Segmentation; joint optic disc and cup segmentation; EfficientNet; attention; glaucoma; residual depth-wise separable convolution
• ISSN: 1662-453X; 1662-4548; 1662-453X
• DOI: 10.3389/fnins.2023.1139181

Glaucoma is the leading cause of irreversible vision loss. Accurate Optic Disc (OD) and Optic Cup (OC) segmentation is beneficial for glaucoma diagnosis. In recent years, deep learning has achieved remarkable performance in OD and OC segmentation. However, OC segmentation is more challenging than OD segmentation due to its large shape variability and cryptic boundaries that leads to performance degradation when applying the deep learning models to segment OC. Moreover, the OD and OC are segmented independently, or pre-requirement is necessary to extract the OD centered region with pre-processing procedures. In this paper, we suggest a one-stage network named EfficientNet and Attention-based Residual Depth-wise Separable Convolution (EARDS) for joint OD and OC segmentation. In EARDS, EfficientNet-b0 is regarded as an encoder to capture more effective boundary representations. To suppress irrelevant regions and highlight features of fine OD and OC regions, Attention Gate (AG) is incorporated into the skip connection. Also, Residual Depth-wise Separable Convolution (RDSC) block is developed to improve the segmentation performance and computational efficiency. Further, a novel decoder network is proposed by combining AG, RDSC block and Batch Normalization (BN) layer, which is utilized to eliminate the vanishing gradient problem and accelerate the convergence speed. Finally, the focal loss and dice loss as a weighted combination is designed to guide the network for accurate OD and OC segmentation. Extensive experimental results on the Drishti-GS and REFUGE datasets indicate that the proposed EARDS outperforms the state-of-the-art approaches. The code is available at https://github.com/M4cheal/EARDS.