文献速递腹部CT

基于深度学习的重建算法改善肝脏CT图像质量并降低辐射剂量:一项对比研究

Improved image quality and dose reduction in liver CT using deep learning-based reconstruction: A comparative study.
PubMed 文献 · Eur J Radiol · 2025-11-18

研究纳入153例至少有一个肝脏局灶性病变的患者,分别使用采用DLIR和HIR的两台CT扫描仪进行两次CT检查,比较图像质量与辐射剂量。结果显示DLIR重建图像的总体中位图像质量评分显著高于HIR,各解剖区域CT衰减值更高、SD更低,SNR和CNR更高,且辐射剂量显著更低。

要点

  • DLIR重建肝脏CT图像总体中位质量评分为4分(范围4-5),显著高于HIR的4分(范围3-4),p<0.001。
  • DLIR图像各解剖区域CT衰减值显著更高、SD显著更低(均p<0.001)。
  • DLIR组辐射剂量显著低于HIR组(p<0.001)。

核心结论

  • DLIR在肝脏CT成像中显著降低辐射剂量,同时在定性和定量两方面改善图像质量。

研究设计与样本

  • 对比研究,纳入153例至少有一个肝脏病变(包括肝囊肿、血管瘤、肝细胞癌和胆管癌)的患者,使用分别采用DLIR和HIR的两台不同扫描仪进行两次CT扫描;图像质量采用5点Likert量表评估,在门静脉分叉水平的轴位平面上手动绘制ROI测量CT衰减值、图像噪声(ROI的标准差SD)、SNR和CNR,辐射剂量通过CTDI和DLP评估。

关键影像表现/征象

  • DLIR重建图像总体中位图像质量评分为4分(范围4-5),HIR为4分(范围3-4),DLIR显著更高(p<0.001)。
  • DLIR重建图像在所有解剖区域的CT衰减值显著高于HIR,SD值显著低于HIR(均p<0.001)。
  • DLIR重建图像的SNR和CNR值更高,所有解剖区域差异均显著(均p<0.001)。

诊断标准与关键数值

  • 图像质量采用5点Likert量表评估,DLIR总体中位评分为4分(范围4-5),HIR为4分(范围3-4),p<0.001。
  • CT衰减值以HU记录,ROI置于肝脏病变、肝实质、椎旁肌(背阔肌)、主动脉腔、门静脉腔和脂肪组织(前腹壁皮下脂肪处,门静脉分叉对应轴位平面)。
  • 图像噪声以ROI的标准差(SD)表示,并计算SNR和CNR;DLIR组各解剖区域CT衰减值显著更高、SD显著更低(均p<0.001),SNR和CNR更高(均p<0.001)。
  • 辐射剂量通过CTDI和DLP评估,DLIR组显著低于HIR组(p<0.001)。

临床应用与阅片要点

  • 在肝脏CT阅片与报告时,DLIR重建图像较HIR具有更高的客观噪声相关指标(更高SNR、CNR)和主观质量评分,且辐射剂量更低。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVES: To evaluate and compare the image quality and radiation dose of CT images reconstructed with Deep Learning-based Image Reconstruction (DLIR) and Hybrid Iterative Reconstruction (HIR) algorithms in patients with focal liver lesion(s).

METHODS: A total of 153 patients with at least one hepatic lesion (including hepatic cysts, hemangiomas, hepatocellular carcinomas, and cholangiocarcinomas) underwent two CT scans. The scans were performed using two different scanners, which employ DLIR and HIR, respectively. Image quality was evaluated using a 5-point Likert scale. CT attenuation values, expressed in Hounsfield units (HU), were recorded within manually drawn regions of interest (ROI) in liver lesions, liver parenchyma, paraspinal muscle (latissimus dorsi), aortic lumen, portal vein lumen, and adipose tissue, measured at the level of the subcutaneous fat of the anterior abdominal wall, at the axial plane corresponding to the bifurcation of the portal vein. Image noise, expressed as ROI's standard deviation (SD), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were calculated. Radiation dose was assessed through the Computed Tomography Dose Index (CTDI) and Dose Length Product (DLP) values.

RESULTS: A total of 306 hepatic lesions were analyzed. The overall median image quality score for CT images reconstructed using the DLIR algorithm was significantly higher than that for HIR [4 (range 4-5) vs. 4 (range 3-4), p < 0.001]. CT attenuation values were significantly higher, and SD values significantly lower, in all anatomic regions in images reconstructed with DLIR compared to HIR (all p < 0.001). SNR and CNR values were higher in CT images reconstructed with DLIR, with significant differences observed across all anatomical regions (all p < 0.001). Additionally, the radiation dose was significantly lower in the DLIR compared to the HIR group (p < 0.001).

CONCLUSIONS: DLIR achieves a significant reduction in radiation dose for liver CT imaging, while also improving image quality both qualitatively and quantitatively.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Maino C, Franco PN, Szafranska E, et al. Improved image quality and dose reduction in liver CT using deep learning-based reconstruction: A comparative study. Eur J Radiol. 2025. PMID: 41264979. doi:10.1016/j.ejrad.2025.112520

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。