NVIDIA Focusing On Deep Learning For Detecting Eye Disease

NVIDIA Focusing On Deep Learning For Detecting Eye Disease

NVIDIA Focusing On Deep Learning For Detecting Eye Disease

Macular degeneration and Age-related macular degeneration, known as AMD, is a leading cause of vision loss and blindness for Americans over 50. So far There’s no cure.

“People (with AMD) are suffering. Everywhere you look, there’s a blurry spot in the center,” said Dr. Aaron Lee, a University of Washington opthamologist and assistant professor who specializes in problems of the retina

Lee believes AI can help with AMD that cause vision loss, Eye showing advanced macular degeneration, Advanced macular degeneration. Nvidia GPU-accelerated deep learning is putting its focus on healthcare again and now EYE care. NVIDIA AI Technology can detect signs of disease that doctors miss, or speed up diagnosis so doctors can start treatments sooner than they usually do, Lee believes. Lee is developing deep learning algorithms that spot AMD and macular edema, a condition that damages central vision. This spotting and detection can lead to much more treatment options for the patients. Among medical fields, ophthalmology is one of the the best suited to benefit from Nvidia GPU-accelerated deep learning and AI detection technology, Lee mentioned.

The Test called optical coherence tomography (OCT), that uses light waves to take cross-section pictures of the retina in eye. Doctors should perform about five million OCT tests a year to be able to diagnose conditions like AMD, glaucoma and diabetic retinopathy. Researchers linked 100,000 patient OCT scans to their electronic health records to create the AMD-detecting algorithm, making a great database for the NVIDIA GPUs to make the analysis and learn from. They trained a neural network to identify patients with AMD based on the learning path, reaching an accuracy rate of about 93 percent, using the NVIDIA CUDA parallel computing on NVIDIA AI VOLTA based GPUs and GeForce GTX TITAN X GPUs with the cuDNN-accelerated Python Caffe deep learning framework. That AMD algorithm in the new Nvidia based system was done about only three weeks, somthing that would take much longer in a regular machine. Here is Lee on advantages of GPU-accelerated deep learning.

“I saw there was something amazing going on here,” he said. “It would have been impossible using regular computer architecture to process a dataset of that size and train a neural network as large as the one that we used.”

Tags: Technology, nvidia, nvda, nvidia ai, ai, ai in healthcare, nvidia ai in eye care, AMD, Age-related macular degeneration, Age-related macular degeneration AMD,

Mohsen Daemi
Latest posts by Mohsen Daemi (see all)