Researchers Develop New Imaging Tool for Earlier Cancer Detection

University of Texas at Dallas researchers have developed a micro imaging device that could be used with an endoscope to spot cancers at an earlier stage.

The technology uses LED lighting and hyperspectral imaging to capture near-infrared and ultraviolet wavelengths in addition to the visible light that a conventional camera registers. The Erik Jonsson School of Engineering and Computer Science researchers published a study describing their compact prototype in the May/June issue of the Journal of Medical Imaging.

Hyperspectral imaging, originally used in satellite imagery, orbiting telescopes and other applications, goes beyond what the human eye can see as cells are examined under ultraviolet and near-infrared lights at micrometer resolution. By analyzing how cells reflect and absorb light across the electromagnetic spectrum, experts can get a spectral image of cells that is as unique as a fingerprint.

"With hyperspectral imaging, we can add potentially hundreds of narrow wavelengths of light to reveal subtle differences in tissue in real-time that a standard camera cannot detect," said Dr. Baowei Fei, professor of bioengineering, director of the Center for Imaging and Surgical Innovation and the study's corresponding author. "Different types of tissue have unique spectral signatures that potentially can help physicians detect cancer cells more accurately."

Supported by the National Institutes of Health and the Cancer Prevention & Research Institute of Texas (CPRIT), Fei and his research team in the Quantitative BioImaging Laboratory have worked for years to advance hyperspectral imaging combined with artificial intelligence (AI) to identify and predict the presence of cancer cells.

Fei, holder of the Cecil H. and Ida Green Chair in Systems Biology Science at UT Dallas and a professor of radiology at UT Southwestern Medical Center, demonstrated the imaging technology's promise for accurately and quickly identifying cancer cells in a 2019 study.

In the most recent report, researchers described how they miniaturized the technology enough to be integrated into devices such as an endoscope, which is used to diagnose and treat conditions affecting the digestive system.

The prototype uses an LED-based approach to capture hyperspectral data fast enough to produce real-time images during medical procedures. The device has been tested on tissue samples but requires further testing before it can be used on patients.

Digestive system cancers are among the most common cancers, with 362,200 diagnoses and 174,520 deaths expected this year in the U.S., according to the American Cancer Society. Standard endoscopy can miss about 10% of gastrointestinal cancers, which include cancers of the esophagus, pancreas, stomach, colon, rectum, anus, liver, gallbladder and small intestine.

Ultimately, Fei aims to develop hyperspectral technology that can be useful for many different cancers and that is small enough to be placed in handheld, affordable personal devices such as a smartphone or pen that individuals could use to scan the skin or mouth, for example.

"Basically, you could complete the scan, and the information would be wirelessly transferred to the cloud. Then, AI may determine the lesion is suspicious and refer the person to a medical center for follow-up," Fei said. "Our goal is to produce imaging systems that are really affordable as well as cost-effective, meaning they could find cancers at earlier stages and reduce the need for unnecessary tissue removal and testing."

"Our goal is to produce imaging systems that are really affordable as well as cost-effective, meaning they could find cancers at earlier stages and reduce the need for unnecessary tissue removal and testing."

Dr. Baowei Fei, professor of bioengineering and holder of the Cecil H. and Ida Green Chair in Systems Biology Science

Other contributors to the study include first author Naeeme Modir, a biomedical engineering doctoral student; Dr. Ling Ma, bioengineering research associate; and former UT Dallas researchers James Dormer and Dr. Maysam Shahedi.

The research was supported by National Cancer Institute grants R01CA288379 and R01CA204254, and CPRIT awards RP240289 and RP240542.

Media Contact: Kim Horner, UT Dallas, 972-883-4463, [email protected], or the Office of Media Relations, UT Dallas, (972) 883-2155, [email protected].