Our paper ‘Quantification of Key Retinal Features in Early and Late Age-Related Macular Degeneration Using Deep Learning’, by Liefers et al, has been published in the American Journal of Ophthalmology. In this paper, we developed and validated a deep learning model for segmentation of 13 features associated with neovascular and atrophic age-related macular degeneration (AMD) in optical coherence tomography (OCT) volumes. This was done in collaboration with Moorfields Eye Hospital in London.
We showed that the proposed automatic segmentation model performs at the level of experienced graders. The application of this model will open numerous new opportunities for study of morphologic retinal changes and treatment efficacy in real-world settings. Furthermore, it can facilitate structured reporting in the clinic, which will reduce subjectivity in clinicians’ assessments and enable implementation of refined treatment guidelines. This could ultimately lead to increased speed of interpretation, a reduction of cost, and improved personalized care.
Example of the model output on a full optical coherence tomography (OCT) volume.