Department of Radiology, Massachusetts General Hospital, White 270, 55 Fruit Street, Boston, MA, 02114, USA.
Eur Radiol. 2021 Nov;31(11):8342-8353. doi: 10.1007/s00330-021-07952-4. Epub 2021 Apr 23.
To investigate the image quality and perception of a sinogram-based deep learning image reconstruction (DLIR) algorithm for single-energy abdominal CT compared to standard-of-care strength of ASIR-V.
In this retrospective study, 50 patients (62% F; 56.74 ± 17.05 years) underwent portal venous phase. Four reconstructions (ASIR-V at 40%, and DLIR at three strengths: low (DLIR-L), medium (DLIR-M), and high (DLIR-H)) were generated. Qualitative and quantitative image quality analysis was performed on the 200 image datasets. Qualitative scores were obtained for image noise, contrast, small structure visibility, sharpness, and artifact by three blinded radiologists on a 5-point scale (1, excellent; 5, very poor). Radiologists also indicated image preference on a 3-point scale (1, most preferred; 3, least preferred). Quantitative assessment was performed by measuring image noise and contrast-to-noise ratio (CNR).
DLIR had better image quality scores compared to ASIR-V. Scores on DLIR-H for noise (1.40 ± 0.53), contrast (1.41 ± 0.55), small structure visibility (1.51 ± 0.61), and sharpness (1.60 ± 0.54) were the best (p < 0.05) followed by DLIR-M (1.85 ± 0.52, 1.66 ± 0.57, 1.69 ± 0.59, 1.68 ± 0.46), DLIR-L (2.29 ± 0.58, 1.96 ± 0.61, 1.90 ± 0.65, 1.86 ± 0.46), and ASIR-V (2.86 ± 0.67, 2.55 ± 0.58, 2.34 ± 0.66, 2.01 ± 0.36). Ratings for artifacts were similar for all reconstructions (p > 0.05). DLIRs did not influence subjective textural perceptions and were preferred over ASIR-V from the beginning. All DLIRs had a higher CNR (26.38-102.30%) and lower noise (20.64-48.77%) than ASIR-V. DLIR-H had the best objective scores.
Sinogram-based deep learning image reconstructions were preferred over iterative reconstruction subjectively and objectively due to improved image quality and lower noise, even in large patients. Use in clinical routine may allow for radiation dose reduction.
• Deep learning image reconstructions (DLIRs) have a higher contrast-to-noise ratio compared to medium-strength hybrid iterative reconstruction techniques. • DLIR may be advantageous in patients with large body habitus due to a lower image noise. • DLIR can enable further optimization of radiation doses used in abdominal CT.
研究单能腹部 CT 基于正弦图的深度学习图像重建 (DLIR) 算法与标准 care 强度的 ASIR-V 的图像质量和感知。
在这项回顾性研究中，50 名患者（62%为女性；56.74±17.05 岁）接受门静脉期扫描。生成了 4 种重建（ASIR-V 为 40%，以及 3 种强度的 DLIR：低（DLIR-L）、中（DLIR-M）和高（DLIR-H））。200 个图像数据集进行了定性和定量图像质量分析。三位盲法放射科医生对图像噪声、对比度、小结构可见度、锐度和伪影进行了 5 分制（1，极好；5，非常差）的定性评分。放射科医生还对图像偏好进行了 3 分制（1，最偏好；3，最不偏好）的评分。定量评估通过测量图像噪声和对比噪声比（CNR）来进行。
与 ASIR-V 相比，DLIR 具有更好的图像质量评分。DLIR-H 的噪声（1.40±0.53）、对比度（1.41±0.55）、小结构可见度（1.51±0.61）和锐度（1.60±0.54）评分最好（p<0.05），其次是 DLIR-M（1.85±0.52、1.66±0.57、1.69±0.59、1.68±0.46）、DLIR-L（2.29±0.58、1.96±0.61、1.90±0.65、1.86±0.46）和 ASIR-V（2.86±0.67、2.55±0.58、2.34±0.66、2.01±0.36）。所有重建的伪影评分相似（p>0.05）。DLIR 从一开始就不影响主观纹理感知，并且比 ASIR-V 更受青睐。所有的 DLIRs 都比 ASIR-V 具有更高的 CNR（26.38-102.30%）和更低的噪声（20.64-48.77%）。DLIR-H 的客观评分最好。
基于正弦图的深度学习图像重建在主观和客观上均优于迭代重建，因为其图像质量更高，噪声更低，即使在体型较大的患者中也是如此。在临床常规中使用可能会降低辐射剂量。
• 与中强度混合迭代重建技术相比，深度学习图像重建（DLIRs）具有更高的对比噪声比。• 由于图像噪声较低，DLIR 可能对体型较大的患者有利。• DLIR 可以进一步优化腹部 CT 中使用的辐射剂量。
