NVIDIA builds partnerships, offers tools to use AI in imaging

NVIDIA is expanding its footprint into radiology by establishing more partnerships and developing tools to assist radiologists.

The company says it’s now working with 75 partners, including several academic medical centers and the National Institutes of Health, to advance the use of artificial intelligence in radiology practice.

In sum, NVIDIA executives now say the company is working with partners including medical centers, medical imaging companies, research institutes, healthcare startups and other provider organizations. The company is growing from its base of developing graphic processing units (GPUs) that enable display of radiological images.

At the recent annual meeting of the Radiological Society of North America, NVIDIA released a software development kit (SDK) for its Clara platform, which enables the creation and deployment of advanced imaging applications and AI-enabled workflows.

With the newly available Clara SDK, developers can easily take advantage of any GPU platform they have to deploy AI, visualization or computer-intensive applications, such as image reconstruction.



The MGH & BWH Center for Clinical Data Science has adopted NVIDIA Clara SDK as part of its strategy to deploy artificial intelligence. The center—jointly supported by Massachusetts General Hospital and Brigham and Women’s Hospital as well as two other partners—is developing an abdominal aortic aneurysm detection model aided by the NVIDIA technology.

To boost the radiology industry’s ability to build and adapt AI applications, NVIDIA has announced two key technologies. Its AI Assisted Annotation SDK enables radiologists to unlock the value of their data faster than traditional annotation methods. And the Transfer Learning Toolkit for Medical Imaging enables physicians to customize and adapt AI applications to their own patients.

NVIDIA also is partnering with the National Institutes of Health, which runs the largest research hospital in the U.S., conducting over 1,600 trials a year. Through the partnership, NVIDIA will co-locate researchers and engineers with clinicians at the NIH Clinical Center, with an initial project of investigating AI tools to streamline clinical trials for brain and liver cancer.

The co-development will also focus on developing AI tools that combine imaging, genomic and clinical data to deliver precision medicine to cancer patients. This will be delivered through a specialized AI data-centric platform and deep learning-based radiomics.

“Applying a powerful tool such as deep learning to medicine will require a truly multidisciplinary team of physicians, hospitals and computer scientists to work together to help realize the potential of computer models for medical imaging, and to help develop predictive imaging biomarkers,” said Elizabeth Jones, MD, director of the Radiology and Imaging Sciences Department at the NIH Clinical Center.

Currently, radiologists use manual measurements of tumors to determine cancer staging based on existing guidelines. Researchers are hoping that AI will transform the process by automatically characterizing and measuring tumors. Also, AI has the potential to improve the accuracy of cancer staging by incorporating data beyond the size of the tumor and other currently used staging criteria. For example, novel imaging biomarkers, discovered by AI, can be used in clinical trials to get us a step closer towards predictive and personalized precision medicine, says Abdul Hamid Halabi, NVIDIA’s global business development lead for healthcare and life sciences.