Novel machine learning framework for the classification of non-mydriatic retinal images
The broader impact and commercial potential of this project is an artificial intelligence (AI)-based method to screen diabetic retinopathy (DR). DR represents the leading cause of vision impairment and blindness in the US. Indeed, it affects almost 4 million people in the US and is associated with direct annual costs of almost $500 M. If diagnosed early, clinical treatment and lifestyle changes can halt the progression of the disease, preventing blindness. However, retinal exams currently require expensive equipment and invasive eye dilation that restrict screenings to ophthalmology or optometry practices. However, this could lead to the under-diagnosis of the condition, particularly in underserved populations. This project advances a system with a new camera and a machine learning approach to enable recognition of DR and other retinal disorders by clinicians.
Ai-Ris seeks is developing a novel software-enabled non-mydriatic fundus camera that can identifiy diabetic retinopathy. The proposed innovation consists of:
1) A portable camera that uses near-infrared (NIR) light, invisible to the human eye. The camera can illuminate the retina and acquire fundus images, enabling the use of the device by non-specialists.
2) A novel framework based on transfer learning, which trains Neural Networks with a limited amount of training data (100 images).
In this project, a prototype system will collect NIR retinal images, with the goal of developing an AI classification algorithm capable of processing these images. In parallel, Ai-Ris will develop a new image processing algorithm. The aim is to improve the resolution of the NIR images, based on contrast normalization methods and noise reduction techniques.