Macular atrophy (MA) is an irreversible endpoint of age-related macular degeneration (AMD) which results in the leading cause of blindness in the world. Early detection is therefore an unmet need. We have developed a novel automated method to identify MA in patients undergoing fol-low-up with optical coherence tomography (OCT) for AMD based on the combination of 2D and 3D Unet architecture. Our automated detection of MA relies on specific structural changes in OCT including 6 established atrophy-associated lesions. Using 1241 volumetric OCTs from 125 eyes (89 patients), the performance of this combination Unet architecture is extremely encouraging, with a mean dice similarity coefficient score of 0.90±0.14 and a mean F1 score of 0.89±0.14. These prom-ising results have indicated superiority when compared to human graders with a mean similarity of 0.71±0.27. We believe this deep learning-aided tool would be useful to monitor patients with AMD, enabling early detection of MA and supporting clinical decisions.