The pace at which medical imaging technology is growing is astounding. Thanks to this, artificial intelligence (AI) can now expose first signs of blindness. A team of researchers from DeepMind in collaboration with Moorfields Eye Hospital and UCL Institute of Ophthalmology, London UK, have developed a new technique which uses deep learning to diagnose vision-threatening diseases.
The researchers use a large dataset of eye scans obtained through optical coherence tomography (OCT). The AI framework consists of raw OCT scans as inputs, a deep segmentation network which is trained with manually segmented OCT scans, a tissue segmentation map and ultimately a deep classification network trained with tissue maps of confirmed diagnoses and optimal referral decisions.
This system by DeepMind has proven to be successful with prediction accuracy being more than 90 percent correct. It can be a boon if implemented on a large scale across hospitals and healthcare institutions. Dr Pearse Keane, who is a consultant ophthalmologist at Moorfields said, “The AI technology we’re developing is designed to prioritise patients who need to be seen and treated urgently by a doctor or eye care professional. If we can diagnose and treat eye conditions early, it gives us the best chance of saving people’s sight.”
With India having more than 50 million people suffering from vision problems in the last few years, setting up an AI-powered system like this will certainly aid in a faster and effective eye diagnosis.
Try deep learning using MATLAB