News | Ultrasound Imaging | May 28, 2019

Improved Imaging for Prostate Cancer Could Lead to More Effective Treatment

Interdisciplinary project seeks to improve outcomes for high-risk prostate cancer patients

Improved Imaging for Prostate Cancer Could Lead to More Effective Treatment

The picture shows that time series signal is extracted from a series of ultrasound frames for classification. Each patch across a number of frames inside the prostate is classified into either cancerous or normal tissue. The image at the lower right corner shows the overall result for those frames. Image courtesy of Pingkun Yan and researchers from NIH, University of British Columbia and Queens University.

May 28, 2019 — Engineers at Rensselaer Polytechnic Institute are working to improve imaging methods in order to make medicine more precise and personalized. This work will be a critical component of a new interdisciplinary research project funded with $1.4 million from the National Institutes of Health (NIH) that seeks to improve radiation therapy for high-risk prostate cancer patients.

“In order to do precision medicine, you need to see better,” said Pingkun Yan, assistant professor of biomedical engineer at Rensselaer. “If you cannot see, you can’t do anything.”

Yan’s expertise in imaging will support researchers from University of Texas Southwestern, led by Jing Wang, associate professor of radiation oncology, who are currently conducting a clinical trial using an approach known as stereotactic body radiation therapy (SBRT), which delivers high doses of radiation directly to a tumor.

Multiple clinical trials have shown that high doses of radiation to prostate tumors can result in improved cancer outcomes, Yan said, but delivery of that radiation must be localized and precise to protect other healthy tissue nearby.

One of the challenges with SBRT is that the prostate can move and deform during delivery. To make sure the accurate dose is being given in the right location, a reliable and accurate tumor tracking method is needed. But traditional ultrasound technology is not sensitive enough to differentiate between the prostate tumor and healthy tissue.

That’s where Yan comes in. He and his team will develop an imaging method to help researchers distinguish between the healthy tissue and the tumor, so they can more accurately administer the radiation doses.

More specifically, Yan will integrate SBRT with a temporal enhanced ultrasound method (TeUS) that he previously developed through a collaboration with the University of British Columbia, Queens University and NIH. TeUS combines a series of ultrasound images, over time, so that researchers and doctors can visually separate the tumor from the healthy organ.

“The tumor and the healthy tissue move a little differently. By observing that area over time, we extract a difference,” he said.

Deep-learning techniques employed by Yan’s team will make this technique possible.

“We could obtain these images in the past, but didn’t have a good tool to analyze those images. With deep learning, with artificial intelligence, we are now able to decode the information and make it usable,” Yan said.

This research is a prime example of the work being done by Yan and other members of the Center for Biotechnology and Interdisciplinary Studies (CBIS) at Rensselaer. Yan is also part of a Cancer Research Group within the center.

Yan also recently received a Bench-to-Bedside award grant, also from NIH, to focus on improving cancer detection through ultrasound imaging. He hopes the results of these collaborative, interdisciplinary projects will improve treatment for all patients.

For more information: dial.rpi.edu

Related Content

Graphic courtesy Pixabay

Graphic courtesy Pixabay

Feature | Artificial Intelligence | July 15, 2019 | By Greg Freiherr
Siemens has long focused on automation as a way to make diagnostic equipment faster and more efficient.
Videos | Artificial Intelligence | July 12, 2019
Khan Siddiqui, M.D., founder and CEO of HOPPR, discusses the economic advantages and costs presented by...
Videos | Digital Pathology | July 11, 2019
Toby Cornish, M.D., Ph.D., associate professor and medical director of informatics at the University of Colorado Scho
FDA Clears Koios DS Breast 2.0 AI-based Software
News | Ultrasound Women's Health | July 11, 2019
Koios Medical announced its second 510(k) clearance from the U.S. Food and Drug Administration (FDA).
360 Photos | Ultrasound Imaging | July 11, 2019
This 360 degree photo shows a basic, point-of-care cardiac echocardiogram being performed using a smartphone turned i
SimonMed Imaging Implements ProFound AI for 3-D Tomosynthesis
News | Mammography | July 10, 2019
Arizona-based SimonMed Imaging announced their implementation of the first U.S. Food and Drug Administration (FDA)-...
IBA Launches Monte Carlo Patient QA for Varian Halcyon at AAPM 2019
Technology | Quality Assurance (QA) | July 10, 2019
IBA announced the launch of the latest functionality of the SciMoCa Monte Carlo Patient QA solution at the 61st annual...
Researchers Use Artificial Intelligence to Deliver Personalized Radiation Therapy
News | Radiation Therapy | July 09, 2019
New Cleveland Clinic-led research shows that artificial intelligence (AI) can use medical scans and health records to...
360 Photos | Ultrasound Imaging | July 09, 2019
A view of a mitral valve on a GE Healthcare Vivid E95 ...
The Beamscan 3-D water phantom with the Varian Halcyon radiotherapy system

The Beamscan 3-D water phantom with the Varian Halcyon radiotherapy system. Image courtesy of PTW.

News | Quality Assurance (QA) | July 08, 2019
At this year’s American Association of Physicists in Medicine (AAPM) show, July 14-18 in San Antonio, Texas, PTW will...