Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, China.
Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, China.
Eur J Radiol. 2022 Jan;146:110070. doi: 10.1016/j.ejrad.2021.110070. Epub 2021 Nov 24.
To assess the image quality (IQ) of low tube voltage coronary CT angiography (CCTA) images reconstructed with deep learning image reconstruction (DLIR).
According to body mass index (BMI), eighty patients who underwent 70kVp CCTA (Group A, N = 40, BMI ≤ 26 kg/m2) or 80kVp CCTA (Group B, N = 40, BMI > 26 kg/m2) were prospectively included. All images were reconstructed with four algorithms, including filtered back-projection (FBP), adaptive statistical iterative reconstruction-Veo at a level of 50% (ASiR-V50%), and DLIR at medium (DLIR-M) and high (DLIR-H) levels. Image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and edge rise distance (ERD) within aorta root and coronary arteries were calculated. The IQ was subjectively evaluated by using a 5-point scale.
Compared with FBP, ASiR-V50% and DLIR-M, DLIR-H led to the lowest noise (Group A: 24.7 ± 5.0HU; Group B, 21.6 ± 2.8 HU), highest SNR (Group A, 24.9 ± 5.0; Group B, 28.0 ± 5.8), CNR (Group A, 42.2 ± 15.2; Group B, 43.6 ± 10.5) and lowest ERD (Group A, 1.49 ± 0.30 mm; Group B, 1.50 ± 0.22 mm) with statistical significance (all P < 0.05). For the objective assessment, the percentages of 4 and 5 IQ scores were significantly higher for DLIR-H (Group A, 93.8%; Group B,90.0%) and DLIR-M (Group A, 85.6%; Group B,86.9 %) compared to ASiR-V50% (Group A, 58.8%; Group B, 58.8%) and FBP (Group A, 34.4%; Group B, 33.1%) algorithms (all P < 0.05).
The application of DLIR significantly improves both objective and subjective IQ in low tube voltage CCTA compared with ASiR-V and FBP, which may promote a further radiation dose reduction in CCTA.
评估深度学习图像重建（DLIR）在低管电压冠状动脉 CT 血管造影（CCTA）图像中的图像质量（IQ）。
根据体重指数（BMI），前瞻性纳入 80 例行 70kVp CCTA（A 组，N=40，BMI≤26kg/m2）或 80kVp CCTA（B 组，N=40，BMI>26kg/m2）的患者。所有图像均采用四种算法重建，包括滤波反投影（FBP）、自适应统计迭代重建-Veo 水平为 50%（ASiR-V50%）和中（DLIR-M）和高（DLIR-H）水平的 DLIR。计算主动脉根部和冠状动脉内的图像噪声、信噪比（SNR）、对比噪声比（CNR）和边缘上升距离（ERD）。使用 5 分制对 IQ 进行主观评估。
与 FBP、ASiR-V50%和 DLIR-M 相比，DLIR-H 导致最低的噪声（A 组：24.7±5.0HU；B 组：21.6±2.8 HU）、最高的 SNR（A 组：24.9±5.0；B 组：28.0±5.8）、CNR（A 组：42.2±15.2；B 组：43.6±10.5）和最低的 ERD（A 组：1.49±0.30mm；B 组：1.50±0.22mm），差异均有统计学意义（均 P<0.05）。对于客观评估，与 ASiR-V50%相比，DLIR-H（A 组：93.8%；B 组：90.0%）和 DLIR-M（A 组：85.6%；B 组：86.9%）和 FBP（A 组：34.4%；B 组：33.1%）算法的 4 分和 5 分 IQ 评分的比例明显更高（均 P<0.05）。
与 ASiR-V 和 FBP 相比，DLIR 在低管电压 CCTA 中显著提高了客观和主观 IQ，这可能会进一步降低 CCTA 的辐射剂量。
