Spatially Enhanced U-Net with Non-Local Attention Gates for Automated Retinal Vasculature and Foveal Avascular Zone Segmentation in OCTA Images
Published in Engineering Applications of Artificial Intelligence, 2026
A spatially enhanced U-Net architecture augmented with non-local attention gates for automated segmentation of retinal vasculature and the foveal avascular zone (FAZ) in optical coherence tomography angiography (OCTA) images.
Recommended citation: Raja, N. P., Sarvesan, S., & Gopi, V. P. (2026). "Spatially Enhanced U-Net with Non-Local Attention Gates for Automated Retinal Vasculature and Foveal Avascular Zone Segmentation in Optical Coherence Tomography Angiography Images." Engineering Applications of Artificial Intelligence, 167, 113956.
Download Paper