Xu Jack J, Lönn Lars, Budtz-Jørgensen Esben, Jawad Samir, Ulriksen Peter S, Hansen Kristoffer L
Department of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100, Copenhagen, Denmark.
Department of Clinical Medicine, University of Copenhagen, 2100, Copenhagen, Denmark.
Abdom Radiol (NY). 2023 Apr;48(4):1536-1544. doi: 10.1007/s00261-023-03845-w. Epub 2023 Feb 21.
To compare noise, contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR) and image quality using deep-learning image reconstruction (DLIR) vs. adaptive statistical iterative reconstruction (ASIR-V) in 0.625 and 2.5 mm slice thickness gray scale 74 keV virtual monoenergetic (VM) abdominal dual-energy CT (DECT).
This retrospective study was approved by the institutional review board and regional ethics committee. We analysed 30 portal-venous phase abdominal fast kV-switching DECT (80/140kVp) scans. Data were reconstructed to ASIR-V 60% and DLIR-High at 74 keV in 0.625 and 2.5 mm slice thickness. Quantitative HU and noise assessment were measured within liver, aorta, adipose tissue and muscle. Two board-certified radiologists evaluated image noise, sharpness, texture and overall quality based on a five-point Likert scale.
DLIR significantly reduced image noise and increased CNR as well as SNR compared to ASIR-V, when slice thickness was maintained (p < 0.001). Slightly higher noise of 5.5-16.2% was measured (p < 0.01) in liver, aorta and muscle tissue at 0.625 mm DLIR compared to 2.5 mm ASIR-V, while noise in adipose tissue was 4.3% lower with 0.625 mm DLIR compared to 2.5 mm ASIR-V (p = 0.08). Qualitative assessments demonstrated significantly improved image quality for DLIR particularly in 0.625 mm images.
DLIR significantly reduced image noise, increased CNR and SNR and improved image quality in 0.625 mm slice images, when compared to ASIR-V. DLIR may facilitate thinner image slice reconstructions for routine contrast-enhanced abdominal DECT.
在0.625毫米和2.5毫米层厚的74千电子伏特灰度虚拟单能（VM）腹部双能量CT（DECT）中，比较使用深度学习图像重建（DLIR）与自适应统计迭代重建（ASIR-V）时的噪声、对比噪声比（CNR）、信噪比（SNR）和图像质量。
本回顾性研究经机构审查委员会和地区伦理委员会批准。我们分析了30例门静脉期腹部快速千伏切换DECT（80/140 kVp）扫描。数据在0.625毫米和2.5毫米层厚下重建为74千电子伏特的ASIR-V 60%和DLIR-High。在肝脏、主动脉、脂肪组织和肌肉内进行定量HU和噪声评估。两名具有委员会认证的放射科医生基于五点李克特量表评估图像噪声、清晰度、纹理和整体质量。
当层厚保持不变时，与ASIR-V相比，DLIR显著降低了图像噪声，提高了CNR以及SNR（p < 0.001）。与2.5毫米的ASIR-V相比，0.625毫米的DLIR在肝脏、主动脉和肌肉组织中测得的噪声略高5.5 - 16.2%（p < 0.01），而0.625毫米的DLIR相比2.5毫米的ASIR-V，脂肪组织中的噪声低4.3%（p = 0.08）。定性评估表明，DLIR的图像质量显著改善，尤其是在0.625毫米图像中。
与ASIR-V相比，DLIR在0.625毫米层厚图像中显著降低了图像噪声，提高了CNR和SNR，并改善了图像质量。DLIR可能有助于常规对比增强腹部DECT的更薄层图像重建。
