Deep Learning Reconstruction Improves the Image Quality of CT Angiography Derived From 80-kVp Cerebral CT Perfusion Data

Yu Chen; Yanling Wang; Tong Su; Min Xu; Jing Yan; Jian Wang; Haozhe Liu; Xiaoping Lu; Yun Wang; Zhengyu Jin

doi:10.1016/j.acra.2023.02.007

Deep Learning Reconstruction Improves the Image Quality of CT Angiography Derived From 80-kVp Cerebral CT Perfusion Data

Acad Radiol. 2023 Nov;30(11):2666-2673. doi: 10.1016/j.acra.2023.02.007. Epub 2023 Sep 26.

Authors

Yu Chen¹, Yanling Wang¹, Tong Su¹, Min Xu², Jing Yan², Jian Wang², Haozhe Liu¹, Xiaoping Lu¹, Yun Wang¹, Zhengyu Jin³

Affiliations

¹ Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences. No.1 Shuai Fu Yuan, Dong Cheng District, Beijing 100730, China.
² Canon medical system (China) Co., Ltd, Beijing, China.
³ Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences. No.1 Shuai Fu Yuan, Dong Cheng District, Beijing 100730, China. Electronic address: jinzy@pumch.cn.

PMID: 37758584
DOI: 10.1016/j.acra.2023.02.007

Abstract

Rationale and objective: To investigate the impact of the deep learning reconstruction (DLR) technique on the image quality of CT angiography (CTA) derived from 80-kVp cerebral CT perfusion (CTP) data and compare it with hybrid-iterative reconstruction (HIR).

Materials and methods: Thirty-three patients underwent CTP at 80 kVp were prospectively enrolled. CTP data were reconstructed with HIR and DLR. Four image datasets were reconstructed: HIR_peak and DLR_peak were single arterial phase images derived from the time point showing the peak value, HIR_tMIP and HIR_tAve were time-resolved maximum intensity projection image and time-resolved average image derived from three time points with the greatest enhancement of HIR. The mean CT values, standard deviation, signal-to-noise ratio, and contrast-to-noise ratio of the internal carotid artery and basilar artery were compared among the four image dataset. Image quality was performed using a five-point rating scale. Arterial stenosis was evaluated.

Results: DLR_peak had the highest CT value and contrast-to-noise ratio in the internal carotid artery and basilar artery (all p < 0.001). DLR_peak showed the best subjective image quality and had the highest score (4.93 ± 0.4) compared to the other three HIR CTA images (all p < 0.001). The degree of vascular stenosis was consistent among the four evaluated sequences (HIR_tAve, HIR_peak, and HIR_tMIP DLR_peak).

Conclusion: For CTA derived from 80-kVp cerebral CTP data, images reconstructed with deep learning showed better image quality and improved intracranial artery visualization than those processed with HIR and other currently used techniques.

Keywords: Cerebral arteries; Computed tomography angiography; Deep learning.