Abstract
Optical coherence tomography angiography (OCTA) is an emerging non-invasive ophthalmic imaging modality. The morphology and contour of the foveal avascular zone (FAZ) are critical biomarkers for the diagnosis of various ophthalmic and systemic diseases; therefore, achieving its accurate segmentation is of substantial clinical significance. To address challenges such as low contrast, indistinct boundaries, and structural confusion with the surrounding retinal vasculature in OCTA images, this paper proposes a multi-scale dilated convolution and dual attention network (MSAD-Net). By integrating a multi-scale dilated convolution module (MSDM) to capture extensive multi-scale contextual information and employing a dual attention module (DAM) to integrate complementary channel and spatial features, thereby synergistically boosting the feature representation of key regions. Experimental results demonstrated that the model achieved superior performance and robust generalization across multiple evaluation metrics, including the Dice similarity coefficient, Jaccard index, precision, and recall-on two public datasets. These findings confirm the robustness of MSAD-Net in the fine segmentation of the FAZ, providing high-precision technical support for the clinical quantitative analysis of ophthalmic diseases.