Coronary CT angiographic detection of in-stent restenosis via deep learning reconstruction

This feasibility study used deep learning reconstruction, Precise IQ Engine (PIQE), to quantify stent strut thickness and lumen vessel diameter, subsequently comparing it with values obtained using conventional reconstruction methods. The authors conducting this study examined 166 stents in 85 consecutive patients who had undergone CT and invasive coronary angiography (ICA) within 3 months of each other.

The results demonstrated that PIQE provided superior image quality as well as superior diagnostic accuracy for in-stent restenosis (ISR), not only for stents measuring ≥ 3.0 mm in diameter but also for those with smaller diameters.

Key points:

• Despite CT technology advancements, evaluating in-stent stenosis severity, especially in small-diameter stents, remains challenging.
• Compared with conventional methods, the Precise IQ Engine uses deep learning to improve spatial resolution.
• Improved diagnostic accuracy of CT angiography helps avoid invasive coronary angiography after coronary artery stenting.

Article: Coronary computed tomography angiographic detection of in-stent restenosis via deep learning reconstruction: a feasibility study

Authors: Hideki Kawai, Sadako Motoyama, Masayoshi Sarai, Yoshihiro Sato, Takahiro Matsuyama, Ryota Matsumoto, Hiroshi Takahashi, Akio Katagata, Yumi Kataoka, Yoshihiro Ida, Takashi Muramatsu, Yoshiharu Ohno, Yukio Ozaki, Hiroshi Toyama, Jagat Narula & Hideo Izawa