Standard CT technology produces spectral images with deep learning algorithms

October 20, 2020 — Bioimaging technologies are the eyes that allow doctors to see inside the body to diagnose, treat and monitor disease. Ge Wang, an endowed professor of biomedical engineering at Rensselaer Polytechnic Institute, has received significant recognition for devoting his research to coupling these imaging technologies with artificial intelligence to improve doctors’ “vision.”

In research published in Groundsa team of engineers led by Wang demonstrated how a deep learning algorithm can be applied to conventional computed tomography (CT) to produce images that would typically require a higher level of imaging technology known as CT dual energy.

Wenxiang Cong, research scientist at Rensselaer, is the first author of this article. Wang and Cong were also joined by co-authors from Shanghai First-Imaging Tech and researchers from GE Research.

“We hope this technique will help extract more information from a regular single-spectrum X-ray scanner, make it more quantitative and improve diagnosis,” said Wang, who is also director of the Imaging Center. biomedical within the Center for Biotechnology and Interdisciplinary Studies (CBIS) at Rensselaer.

Conventional CT scans produce images that show the shape of tissues in the body, but they don’t give doctors enough information about the makeup of those tissues. Even with iodine and other contrast agents, which are used to help doctors tell the difference between soft tissue and the vascular system, it is difficult to distinguish between subtle structures.

A next-level technology called dual-energy CT brings together two sets of data to produce images that reveal both tissue shape and tissue composition information. However, this imaging approach often requires a higher radiation dose and is more expensive due to the additional hardware required.

“With traditional CT, you take a grayscale image, but with dual-energy CT, you take a two-color image,” Wang said. “With deep learning, we’re trying to use the standard machine to do the dual-energy CT imaging job.”

In this research, Wang and his team demonstrated how their neural network was able to produce these more complex images using single-spectrum CT data. The researchers used images produced by dual-energy CT to train their model and found that it was able to produce high-quality approximations with a relative error of less than 2%.

“Professor Wang and his team’s expertise in bioimaging gives physicians and surgeons a ‘fresh look’ in the diagnosis and treatment of disease,” said Deepak Vashishth, Director of CBIS. “This research effort is a great example of the partnership needed to personalize and solve persistent human health issues.”

For more information: www.RPI.educated

Previous Images of the US West Coast on fire
Next New reflective array microscope images mouse brain through intact skull