UCLA awarded $2.7 million to study AI role in improving cancer diagnosis

Share on facebook
Share on twitter
Share on linkedin
Share on email
Share on print

Researchers from the David Geffen School of Medicine at UCLA and UCLA Jonsson Comprehensive Cancer Center have received a $2.7 million grant from NCI to develop techniques to improve the quality of prostate magnetic resonance imaging and new artificial intelligence methods that use prostate MRI to assist cancer diagnosis.

The five-year project, led by Kyung Sung, associate professor of radiology, and Holden Wu, associate professor of radiology, bioengineering and biomedical physics, will help radiologists improve their ability to diagnose prostate cancer and help identify and predict the aggressiveness of the disease.

The new techniques will be evaluated in men who undergo prostate MRI and proceed to biopsy or surgery.

Previous studies led by Sung have shown artificial intelligence can perform as well as experienced radiologists in detecting prostate cancer. Improvements to the current system could help not only save time but potentially provide diagnostic guidance to less-experienced radiologists. Sung and Wu have also developed advanced quantitative MRI techniques that will be combined with artificial intelligence to maximize the performance for prostate cancer diagnosis.

YOU MAY BE INTERESTED IN

Leadership is changing at The Wistar Institute and the Helen F. Graham Cancer Center & Research Institute in the months to come—but the leaders of the two institutions say that this will have little if any effect on the clinical-research collaboration that they have spent the past 15years building (The Cancer Letter, July 12, 2019). 
March is National Colorectal Cancer Awareness Month. It is a reminder of a heartbreaking trend that oncologists like me are witnessing in our clinics: Last year, for the first time, colorectal cancer became the leading cause of cancer-related death in Americans under the age of 50, according to data published earlier this year in JAMA.

Never miss an issue!

Get alerts for our award-winning coverage in your inbox.

Login