UCSF, NVIDIA join to research AI use in medical imaging
UC San Francisco is upping its research into advanced computing in healthcare, launching an artificial intelligence center specifically to advance its use in medical imaging.
The Center for Intelligent Imaging will develop and apply artificial intelligence in the quest to find new ways to use radiology to look inside the body and to evaluate health and disease.
UCSF investigators in the center will work with Santa Clara, Calif-based NVIDIA, which develops AI products to support infrastructure and tools. The collaboration will aim to create new ways to enable the translation of AI into clinical practice.
“Artificial intelligence represents the next frontier for diagnostic medicine,” says Christopher Hess, MD, chair of UCSF’s Department of Radiology and Biomedical Imaging. “The Center for Intelligent Imaging will serve as a hub for the multidisciplinary development of AI in imaging to meet unmet clinical needs and provide a platform to measure impact and outcomes of this technology. The result will be more efficient, higher-value imaging for patients within and outside of UCSF.”
NVIDIA engineers and data scientists will work with UCSF investigators to develop clinical AI tools, applying powerful computational resources, with the goal of accelerating the AI development cycle and integrating it seamlessly in the clinic.
The new UCSF center has the potential to “bring together an innovative ecosystem of startups, vendors, UCSF’s thought leadership in radiology and NVIDIA’s Clara platform on the world’s fastest GPUs, to create imaging AI solutions for improving patient care,” says Abdul Hamid Halabi, director of healthcare at NVIDIA.
Researchers will use patient images and clinical data from UCSF Health and other institutions to develop, test and validate deep learning algorithms. The center’s computational infrastructure includes NVIDIA’s DGX-2 supercomputer. In addition to contributing technology tools, NVIDIA developers will work with UCSF researchers on several AI projects, including brain tumor segmentation, liver segmentation and clinical deployment.
Integrating AI into the radiology workflow can help medical institutions keep pace with an ever-growing stream of medical imaging data, NVIDIA’s Halabi says. The number of images acquired during common studies like MRI and CT scans has swelled in recent years from tens of images each to hundreds or thousands. “It’s a challenge compounded by a rise in the number of patients being imaged,” he adds.
“It makes for an absolutely overwhelming volume of information to digest,” UCSF’s Hess says. “We’re hoping to use AI to help radiologists better navigate and interact with data, to derive more meaning out of images, and to improve the value of medical imaging for the individual patient.”
Nearly 500,000 imaging studies are performed at UCSF annually. The medical center has amassed at least a petabyte of imaging data over the years, ranging from small X-ray images to much larger PET/MRI studies. These bigger files can take up gigabytes or now even terabytes of data storage. Training deep learning models on these massive datasets requires immense computational power. By adopting the high-performance NVIDIA DGX-2, Hess researchers could cut the time to train AI models from months or days down to hours or even shorter.
“The volume of medical imaging has been rapidly increasing, and radiologists are struggling to keep up with the sheer number of images,” says Sharmila Majumdar, a professor and vice chair in the UCSF Department of Radiology and Biomedical Imaging. The center “aims to impact the entire value chain of imaging, from the time the patient comes for a scan to the final delivery of individualized, quantitative, prognostic and care-defining information.”
Hess adds that the university also plans to use AI for quantitative imaging, predictive analytics and resource scheduling, and that’s expected to give medical professionals access to insights that were once too time-consuming to calculate or impossible to find without deep learning methods.
NVIDIA and UCSF are working together to develop AI models that can be deployed into imaging workflow, starting with deep learning models to analyze scans of the brain and liver. For example, when doctors treat brain cancer patients, MRI scans provide critical information about how a tumor is responding to radiation treatment and chemotherapy. Today, radiologists analyze scans visually with manual tools; but AI can provide a quantitative measurement, calculating the precise volume of a tumor. By tracking how a tumor’s volume changes from scan to scan, clinicians can better assess how a patient is responding to treatment.
The team is also developing an AI model that can segment and measure the left and right lobes of an organ donor’s liver from CT images. These metrics are critical for doctors planning liver transplants from a living donor to a patient, and take up to two hours to delineate and compute by hand. With deep learning, Hess estimates, it could be done in seconds.