Put AI to Work
April 15-18, 2019
New York, NY
Please log in

How to use AI to improve efficiency, safety, and patient satisfaction in radiology

Enhao Gong (Subtle Medical), Greg Zaharchuk (Stanford University)
2:40pm3:20pm Thursday, April 18, 2019
AI Business Summit, Case Studies
Location: Sutton North/Center
Secondary topics:  AI case studies, Computer Vision, Health and Medicine

Who is this presentation for?

  • Executives in the healthcare industry



Prerequisite knowledge

  • Familiarity with the healthcare and radiology industry (useful but not required)

What you'll learn

  • Explore a solution developed by Stanford University and Subtle Medical that uses AI to significantly improve speed and quality of radiology


Clinical radiology currently faces several clinical issues: improving imaging efficiency, reducing risks, and developing higher imaging quality. Enhao Gong and Greg Zaharchuk explain how Subtle Medical’s deep learning/AI solution addresses these problems by enabling faster MRI and faster PET and low-dose scans, providing real clinical and financial benefit to hospitals. The products are FDA cleared and pending and have been well received by clinicians. Powered by industry solutions such as Intel OpenVINO, the deployment can be highly accelerated and enables real-time solutions that benefit clinical applications by providing faster, safer smart imaging exams to patients

For faster MRI, the deep learning solution replaces conventional iterative optimization-based algorithms. Using ResNet-based recurrent structure and generative adversarial network-based adversarial loss, the model successfully reconstructs images from low-quality MRI into high-quality MRI with a significantly better signal-to-noise ratio and resolution information. This solution generates results much more efficiently than conventional iterative methods with much better image quality and accuracy.

Gadolinium deposition is one of the most urgent issues facing radiology community. Subtle Medical validated both technical performance and clinical applicability of the developed deep learning technology that algorithmically restores and boosts the contrast information in MRI as well as the generalization and robustness of the solution to show that it improves workflow while maintaining diagnostic quality.

The proposed DL solution demonstrates significant superiority over conventional algorithms and noninferiority with standard slow and high-dose exams. Quantitative metrics demonstrated consistent (>5 dB in PSNR and >10% in SSIM) and significant (p<0.001) quality improvement of the deep learning-based solution, compared with low-dose CE-MRI. Qualitative ratings showed nonsignificant differences in image quality between the DL-enhanced and acquired full-dose CE-MRI images, which was also verified with reader study.

Photo of Enhao Gong

Enhao Gong

Subtle Medical

Enhao Gong is the founder and CEO at Subtle Medical, an AI and radiology startup from Stanford and the winner of 2018 NVIDIA Inception Award at AI+Healthcare. He’s a serial entrepreneur and PhD in electrical engineering at Stanford, with a research focus on applying AI and deep learning to improve reconstruction, analysis, and quantification in medical imaging. His work applies AI to accelerate and reduce doses for MRI and PET and has been featured in numbers of academic journals and clinical conferences. Enhao has won several awards, including being recognized by Forbes China as one of 2018’s “30 under 30.”

Photo of Greg Zaharchuk

Greg Zaharchuk

Stanford University

Greg Zaharchuk is a radiologist and professor in radiology at Stanford University and a neuroradiologist at Stanford Hospital. His research interests include deep learning applications in neuroimaging, imaging of cerebral hemodynamics with MRI and CT, noninvasive oxygenation measurement with MRI, clinical imaging of cerebrovascular disease, imaging of cervical artery dissection, MR/PET in neuroradiology, and resting-state fMRI for perfusion imaging and stroke.