Professor uses computer science to reduce patients’ exposure to radiation from CT scans


Ruogu Fang

Ruogu Fang is an assistant professor of computer science at the College of Engineering and Computing is researching.

When a doctor orders a CT perfusion scan, most people don’t give it a second thought as it’s necessary to evaluate serious medical conditions such as stroke.

Yet, each year, about 15,000 people die because of cancers caused by radiation in CT perfusion scans. An assistant professor of computer science at FIU’s College of Engineering and Computing is researching how to reduce radiation from these scans by using math and computer technology.

Radiation allows scans to render a clear image, and when radiation is reduced, so is the quality of that image. In her research, Ruogu Fang, from the School of Computing and Information Sciences (SCIS), takes CT scan images acquired at normal radiation doses and introduces “noise” in a specific mathematical way to simulate what a scan would look like at a low radiation dose.

Noise refers to irregular grainy patterns that appear in a scan and degrade image quality. Present in all electronic systems, it is caused by electronic interference and the patient’s own body, which emits thermal motion. Fang’s goal is to show that using her original mathematical equation, high quality images may still be obtained without exposing patients to significant amounts of radiation.

“My motivation is to use big data and technology to improve the quality of health care and reduce the risks for patients who are seeking treatment and cure,” said Fang. CT perfusion scans are used to evaluate acute stroke and diagnose tumors, among other uses.

Fang has developed several mathematical algorithms and then tested and validated them on simulated data. She was able to show that the same information can be obtained, if not better, with her mathematical formula, which means decreased radiation exposure for patients. She’s received $175,000 in funding from the National Science Foundation (NSF) and the Ralph Lowe Junior Faculty Enhancement Award from Oak Ridge Associated Universities (ORAU), and now the next step is to validate her technique in actual patients using low-dose CT scans.

Fang first began her research in 2009 as a Ph.D. candidate working at Cornell University’s School of Electrical and Computing Engineering collaborating with Weill Cornell Medical College (WCMC), the university’s medical school and biomedical research unit. While working under the direction of Pina C. Sanelli, her Ph.D. clinical advisor, Fang developed an interest in using computer science to improve health care and outcomes for patients.

Mr. and Mrs. Sidhu present Fang with award.

Mr. and Mrs. Sidhu (left and center) present Fang (right) with award.

“We had a common interest to work together to develop mathematical and statistical software algorithms that would be able to lower the radiation dose from CT perfusion for patients. We wanted to make it a much safer technique,” said Sanelli, vice chairman of research at Northwell Health and an adjunct professor of radiology at Weill Cornell Medical College.

While Fang’s research is focused on stroke patients, her technology has the potential to be applied to other medical conditions, including cardiovascular diseases and kidney dysfunction. It also has the potential for cross-application for MRI use.

SMILE Lab group

SMILE Lab group. From left to right: Jingan Qu, Peng Liu, Asst. Prof. Ruogu Fang, Xing Pang, Yao Xiao and Denial Parra

Fang was honored recently by the Society for Brain Mapping and Therapeutics (SBMT) at its annual international conference held in Miami. She was awarded the first Robin Sidhu Memorial Young Scientist Award for her creativity in applying IT-related principles to solve a challenging clinical problem. The award was open only to applicants younger than 30 years of age.

Fang’s Smart Medical Informatics Learning and Evaluation Lab, or SMILE Lab, focuses on bridging big medical data and health care. With graduate students in her lab, they are currently working on using deep learning to mine the ever-increasing multi-genre medical data, including the brain dynamics imaging, neuron imaging and behavior risk factors. Their research will push the frontier of brain imaging research from lower and safer radiation to a better understanding of brain dynamics.