Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China.
Research Center Institute, United Imaging Healthcare, Shanghai, China.
Eur J Radiol. 2022 Apr;149:110221. doi: 10.1016/j.ejrad.2022.110221. Epub 2022 Feb 15.
To investigate the image quality and feasibility of a novel artificial intelligence iterative reconstruction (AIIR) algorithm for aortic computer tomography angiography (CTA) with a low radiation dose and contrast material (CM) dosage protocol in comparison with hybrid iterative reconstruction (HIR) algorithm for standard-of-care aortic CTA.
Fifty consecutive patients (mean age 58 ± 14 years, mean BMI 24.5 ± 4.7 kg/m) with aortic diseases were prospectively enrolled. All patients underwent at least twice follow-up aortic CTA examinations. Standard dose CT (SDCT) was applied in the initial follow-up examination (100 kVp, auto mAs, contrast dose 0.8 mgL/kg), images were reconstructed with HIR (SDCT-HIR). In the second follow-up examination, patients underwent scanning with low dose CT (LDCT) (70 kVp, auto mAs, contrast dose 0.5 mgL/kg), images were reconstructed with HIR (LDCT-HIR) as well as AIIR (LDCT-AIIR). Attenuation values, noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured for objective analysis. Subjective image quality was rated by two blinded radiologists using a 5-point scale. The effective radiation dose and CM dosage were also recorded.
The effective radiation dose (1.58 ± 0.17 mSv vs. 9.96 ± 1.05 mSv, P < 0.001) and CM dosage (34.38 ± 5.43 ml vs. 54.64 ± 8.63 ml, P < 0.001) achieved a remarkable reduction of 84.14% and 37.08% in the LDCT compared to the SDCT. The attenuation was similar among the three reconstructed images (P > 0.05). Compared to LDCT-HIR images, LDCT-AIIR showed a lower noise and higher SNR and CNR. For qualitative analysis, there were no significant differences between the LDCT-AIIR and the SDCT-HIR images among four metrics (P > 0.05).
Compared to standard-of-care aortic CTA with HIR, the application of the AIIR algorithm allows for radiation dose and CM dosage reduction while preserving image quality on low dose aortic CTA.
与混合迭代重建(HIR)算法相比,评估一种新的人工智能迭代重建(AIIR)算法在低辐射剂量和对比剂(CM)剂量方案下进行主动脉计算机断层血管造影(CTA)的图像质量和可行性,用于标准的主动脉 CTA。
连续前瞻性纳入 50 例主动脉疾病患者(平均年龄 58 ± 14 岁,平均 BMI 24.5 ± 4.7 kg/m)。所有患者均进行了至少两次主动脉 CTA 随访检查。初始随访检查采用标准剂量 CT(SDCT)(100 kVp,自动 mAs,对比剂剂量 0.8 mgL/kg),图像采用 HIR(SDCT-HIR)重建。在第二次随访检查中,患者行低剂量 CT(LDCT)(70 kVp,自动 mAs,对比剂剂量 0.5 mgL/kg)扫描,图像采用 HIR(LDCT-HIR)和 AIIR(LDCT-AIIR)重建。进行客观分析测量衰减值、噪声、信噪比(SNR)和对比噪声比(CNR)。由两名盲法放射科医生使用 5 分制对图像质量进行主观评分。记录有效辐射剂量和 CM 剂量。
与 SDCT 相比,LDCT 实现了有效辐射剂量(1.58 ± 0.17 mSv 比 9.96 ± 1.05 mSv,P < 0.001)和 CM 剂量(34.38 ± 5.43 ml 比 54.64 ± 8.63 ml,P < 0.001)的显著降低,分别降低了 84.14%和 37.08%。三种重建图像的衰减值相似(P > 0.05)。与 LDCT-HIR 图像相比,LDCT-AIIR 噪声更低,SNR 和 CNR 更高。定性分析,四项指标中 LDCT-AIIR 与 SDCT-HIR 图像之间无显著差异(P > 0.05)。
与标准的 HIR 主动脉 CTA 相比,AIIR 算法的应用可以在低剂量主动脉 CTA 中降低辐射剂量和 CM 剂量,同时保持图像质量。