Role of Artificial Intelligence in detecting diseases using eye fundus

Role of Artificial Intelligence in detecting diseases using eye fundus

Retinal imaging helps in detecting early signs of certain diseases in patients. The use of high-resolution retinal imaging can lead to early detection of the following diseases and provide visual evidence of the changes that occur in patients’ eyes over time due to these conditions. Artificial intelligence (AI) plays a vital role in detecting various diseases using eye fundus. We have listed few initiatives and innovations in artificial intelligence and research carried out globally.


Retinal imaging can reveal signs and symptoms of glaucoma, such as damage to the optic nerve caused by excess pressure or increased pressure on blood vessels. “New Innovations in Hacking Glaucoma,” during the Glaucoma Symposium at the 2017 Glaucoma 360 meeting, Robert Chang, MD, an assistant professor of ophthalmology, Stanford University, outlined how the technology might work. Dr. Chang is developing AI for glaucoma.

Age-Related Macular Degeneration:

Retinal imaging can show signs of this disease, including fluid leakage or bleeding in the rear part of the eye.  Dr. Aaron Lee, a University of Washington ophthalmologist and assistant professor and his team linked 100,000 patient OCT scans to their electronic health records to create the AMD-detecting algorithm. They trained a neural network to identify patients with AMD — reaching an accuracy rate of 93 percent — using the CUDA parallel computing platform and our GeForce GTX TITAN X GPUs with the cuDNN-accelerated Python Caffe deep learning framework


High Blood Pressure:

Retinal imaging shows symptoms of high blood pressure such as blood vessels becoming narrower, bleeding in the rear part of the eye or retinal spots. Google involved in application of deep learning to retinal fundus images to predict multiple cardiovascular risk factors, including age, gender and SBP.   These risk factors are core components used in multiple cardiovascular risk calculators indicates that their model can potentially predict cardio-vascular risk directly.


Diabetic Retinopathy:

Retinal imaging helps to detect abnormal changes such as the formation of new blood vessels or leakage in the part of the eye or swelling. Using “deep learning” techniques, researchers in the Google Brain initiative have developed a self-optimiz­ing algorithm that can examine large numbers of fundus photographs and automatically detect diabetic retinopa­thy (DR) and diabetic macular edema (DME) with a high degree of accuracy.



High-resolution images of the retina can reveal early signs of cancer in the eye, such as dark spots that indicate a melanoma. It is in the early days to find a proven prediction approach.

Microsoft has collaborated with Hyderabad-based L V Prasad Eye Institute to launch Microsoft Intelligent Network for Eye care (MINE). IBM is working with Manipal Hospitals in India to bring its Watson technology into cancer diagnosis. Artificial Intelligence will have a significant impact on healthcare. In niche departments such as ophthalmology and oncology, healthcare professionals will benefit from AI-assisted screening and diagnosis.

vDMA has collaborated with a leading ophthalmology hospital in India and Disease Management Analytics being an AI enabled platform actively working on the above areas of research and innovations for better accuracy and predictions.

Share this post