Editor’s note: This is one of four profiles of finalists for NVIDIA’s 2018 Global Impact Award, which provides $200,000 to researchers using NVIDIA technology for groundbreaking work that addresses social, humanitarian and environmental problems.
The noisy, old MRI machine may get a new lease on life.
Magnetic resonance imaging machines in recent years have faced a newer model on the scene, the magnetic resonance angiography machine. MRA units have been heavy lifters for more detailed images of blood vessels, enabling detection of aneurysms and other life-threatening conditions.
Now, researchers have unleashed deep learning on MRI data to mimic the results of MRA equipment. The discovery holds the potential to lower the costs of obtaining the latest and greatest in medical imaging, which would be a boon to hospitals, especially those in rural areas and emerging markets unable to afford an MRA machine.
Aaron Lee, an assistant professor of ophthalmology at the University of Washington, and his team trained deep learning models to make inferences from single-shot structural images from both MRI and OCT (optical coherence tomography) machines, creating angiography imaging from each, respectively.
The pioneering work in medical imaging synthesis with artificial intelligence represents a first of its kind, making assessment of a host of vascular diseases more widely available, Lee said.
“The idea that you can take a single snapshot and extrapolate what’s happening is kind of mind-boggling,” Lee said of the advances poised to boost older machines.
AI for Imaging
The researchers used algorithms to map between OCT and OCTA images as well as between MRI and MRA images, work that was made possible by GPU-accelerated deep learning.
The University of Washington team’s methods could potentially be applied to libraries of medical images to make screening easier for a variety of diseases.
This achievement has placed Lee and his team researchers among four finalists for NVIDIA’s 2018 Global Impact Award. The award provides an annual grant of $200,000 for groundbreaking work that addresses the world’s most important social and humanitarian problems. The 2018 awards will go to researchers or institutions using NVIDIA technology to achieve breakthrough results with broad impact.
GPUs for Imaging
The University of Washington team had nearly 2 terabytes of data but lacked the computing heft to run its algorithms on it. Using CPUs would have taken years to handle the task of processing the dataset, Lee said.
Thanks to advances in deep learning for computer vision and the application of GPUs to benefit a wide array of fields, the researchers were able to go to work on their dataset. The team used NVIDIA TITAN X GPUs running the Pascal architecture to rapidly speed up the training of large deep convolutional neural networks.
“The graphics cards allowed us to do the algebra necessary for deep learning very quickly,” Lee said.
University of Washington’s researchers also run servers outfitted with NVIDIA Tesla P100 GPU accelerators.
Check out the work of last year’s Global Impact Award winners.