Epiretinal membrane (ERM) is an eye disease that affects 7% of the world population, with a higher incidence in people over 75 years old. If left untreated, it can lead to complications in the central vision, resulting in severe vision loss. Early detection is important for progress follow-up, treatment monitoring, and to avoid total vision loss. Optical coherence tomography, a non-invasive retina imaging technique, can be used for effective detection and monitoring of this condition. To date, automatic methods to detect ERM have received little attention in the research literature. This article describes the application of deep learning to the automatic detection of ERM. The proposed solution is based on four widely used convolutional neural network architectures adapted to the task using transfer learning, and fine-tuned with a proprietary dataset. The architectures were specialized by optimizing the network hyperparameters and two loss functions, cross-entropy and focal loss. A detailed description of the methods is provided, complemented with an exhaustive evaluation of their performance. Overall, the methods reached an accuracy of 99.7%, with sensitivity and specificity of 99.47% and 99.93%, respectively. The results showed that transfer learning enabled a successful use of deep learning to detect ERM in optical coherence tomography retinal images, even when only relatively small training datasets are available.INDEX TERMS Artificial intelligence, deep learning, epiretinal membrane, macular puker, neural networks, optical coherence tomography, transfer learning.

No abstract

No abstract