SimpleCNN-UNet: An optic disc image segmentation network based on efficient small-kernel convolutions

Pathological myopia can lead to a series of eye diseases, including glaucoma and retinal pathologies. One of its most significant changes is the alteration in the size of the optic disc area in fundus images. Therefore, precise segmentation of the optic disc area is particularly important in ocular medical diagnosis. Although many well-established methods in medical image segmentation rely on Fully Convolutional Networks (FCNs), they often struggle to capture global context compared to Transformer models. However, incorporating Transformers generally necessitates larger training datasets, which can pose a significant challenge. To address these issues, Convolutional Neural Networks (CNNs) with large convolutional kernels have been proposed as an alternative for capturing contextual information, but they come with increased parameter counts and higher computational costs during training. In this paper, we introduce SimpleCNN-UNet, a lightweight image segmentation network based on small-kernel convolutions. By strategically stacking these small convolutions, we emulate the receptive field of large-kernel convolutions while substantially reducing the number of parameters. Another novel feature of SimpleCNN-UNet is the Multi-Layer Cross-Attention Gate, designed for efficient feature fusion across different levels. To overcome the limited availability of fundus image data, we employed extensive data augmentation techniques on our existing dataset. Our experimental results on the iChallenge-PM, iChallenge-AMD, iChallenge-GON, and IDRiD datasets demonstrate that SimpleCNN-UNet outperforms other image segmentation networks in terms of performance while also offering faster inference speeds and lower training costs. •Propose a fully convolutional medical image segmentation network with efficient small-kernel convolutions.•Introduce the Multi-Layer Cross-Attention Gate to effectively merge features from different levels.•Expand the optic disc image dataset through data augmentation techniques to increase the diversity of the data.