Automatic Refractive Error Estimation Using Deep Learning-Based Analysis of Red Reflex Images

Purpose/Background: We evaluate how a deep learning model can be applied to extract refractive error metrics from pupillary red reflex images taken by a low-cost handheld fundus camera. This could potentially provide a rapid and economical vision-screening method, allowing for early intervention to prevent myopic progression and reduce the socioeconomic burden associated with vision impairment in the later stages of life. Methods: Infrared and color images of pupillary crescents were extracted from eccentric photorefraction images of participants from Choithram Hospital in India and Dargaville Medical Center in New Zealand. The pre-processed images were then used to train different convolutional neural networks to predict refractive error in terms of spherical power and cylindrical power metrics. Results: The best-performing trained model achieved an overall accuracy of 75% for predicting spherical power using infrared images and a multiclass classifier. Conclusions: Even though the model's performance is not superior, the proposed method showed good usability of using red reflex images in estimating refractive error. Such an approach has never been experimented with before and can help guide researchers, especially when the future of eye care is moving towards highly portable and smartphone-based devices.

Retinal Self Examination “Selfies” During a Pandemic

The advancement of smartphone camera technology allowing a smaller, high-resolution forward-facing camera on a smartphone allows a user to see the image they are about to capture of themselves at arm’s length, therefore taking a ‘selfie’ image of themselves. The idea of a ‘selfie’ in a clinical setting is novel, but the exploration of this as a concept has been made necessary as COVID-19 infection and transmission risk is based on the proximity, that is, a susceptible person coming near to the person, who is infected. This report discusses an innovative smartphone-based device, oDocs nun IR, a retinal imaging device, as a tool for taking selfie retinal images/videos by patients, that could be later analyzed by the specialists/optometrists over the teleophthalmology portal.