文献速递神经MR

人工智能辅助增强后脑MRI:对比剂剂量减少百分之八十

AI-Assisted Post Contrast Brain MRI: Eighty Percent Reduction in Contrast Dose.
PubMed 文献 · Acad Radiol · 2024-11-26

这项多中心前瞻性研究纳入101例患者,利用深度学习网络从20%标准剂量钆对比剂的多参数脑MRI生成合成的全剂量增强T1w图像。三位神经放射科医师评分显示,合成图像与全剂量T1w图像在图像质量上无显著差异(P=0.08),图像信噪比和血管清晰度评分更高(P<0.05),并在边界勾勒、内部形态和对比增强方面达到统计学非劣效(P<0.001)。

要点

  • 深度学习合成增强T1w图像与全剂量T1w图像在图像质量上无显著差异(P=0.08)。
  • 合成图像的图像信噪比和血管清晰度评分高于全剂量T1w图像(P<0.05)。
  • 边界勾勒、内部形态和对比增强方面达到统计学非劣效(P<0.001)。

核心结论

  • 所提出的深度学习方法能够生成与全剂量T1w图像相当的合成增强后T1加权MR图像,由定量分析和放射科医师评估确定。

研究设计与样本

  • 多中心前瞻性研究,纳入101例患者,脑MRI采集时间为2024年3月至2024年7月。
  • 纳入白质病变、小血管病、肿瘤或肿块、术后改变及无强化病灶的患者。
  • 采集增强前、低剂量(标准剂量的20%)和标准剂量增强后T1w序列,使用深度学习网络处理增强前和低剂量序列生成合成的全剂量增强T1w图像。
  • 由三位神经放射科医师采用5点Likert量表对图像质量、图像信噪比、血管清晰度和病灶可视化进行评分,并结合自动体素级指标进行定量比较。

关键影像表现/征象

  • 深度学习T1w图像相对于全剂量T1w图像的SSIM为86±12.1%,PSNR为27±3 dB。

诊断标准与关键数值

  • 图像质量平均阅片者评分在深度学习T1w与全剂量T1w之间无显著差异(P=0.08)。
  • 图像信噪比和血管清晰度评分深度学习T1w高于全剂量T1w(P<0.05)。
  • 三位阅片者评估中,边界勾勒、内部形态和对比增强的最小二乘均值差异的95%CI下限均高于非劣效界值(≥-0.26),显示深度学习T1w与全剂量T1w配对图像间统计学非劣效(P<0.001)。

临床应用与阅片要点

  • 深度学习合成增强T1w图像在图像质量上与全剂量T1w图像无显著差异,图像信噪比和血管清晰度评分更高。
  • 边界勾勒、内部形态和对比增强方面达到统计学非劣效。

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: In the context of growing safety concerns regarding the use of gadolinium-based contrast agents in contrast-enhanced MRI, there is a need for dose reduction without compromising diagnostic accuracy. A deep learning (DL) method is proposed and evaluated in this study for predicting full-dose contrast-enhanced T1w images from multiparametric MRI acquired with 20% of the standard dose of gadolinium-based contrast agents.

MATERIALS AND METHODS: This multicentric prospective study leveraged multiparametric brain MRIs acquired between March and July 2024. A total of 101 patients were included. Patients with white matter disease, small vessels disease, tumor or mass, post-operative change and no enhanced lesion were included. Pre-contrast, low-dose, and standard-dose postcontrast T1w sequences were acquired. A DL network was utilized to process pre-contrast and low-dose sequences to generate synthesized full-dose contrast-enhanced T1w images. DL-T1w images and full-dose T1w MRI images were qualitatively and quantitatively compared using both automated voxel-wise metrics and a reader study, in which three neuroradiologists graded the image quality, image SNR, vessel conspicuity and lesion visualization using a 5-point Likert scale.

RESULTS: A comparison of the average reader scores for DL-T1w images and full-dose-T1w images did not show any significant differences in image quality (P = 0.08); however, the image SNR and vessel conspicuity scores were higher for DL-T1w images (P < 0.05). In all 3 reader evaluations, the lower limit of the 95% CI for differences in least square means for border delineation, internal morphology, and contrast enhancement was above the noninferiority margin, showing statistical noninferiority between DL-T1w and full-dose-T1w paired images (≥ -0.26) (P < 0.001). The DL-T1w images obtained an SSIM of 86 ± 12.1% relative to the full-dose-T1w images, and a PSNR of 27 ± 3 dB.

CONCLUSION: The proposed DL method was capable of generating synthesized postcontrast T1-weighted MR images that were comparable to full-dose T1w images, as determined by quantitative analysis and radiologist evaluation.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Ahmadzade M, Morón FE, Shastri R, et al. AI-Assisted Post Contrast Brain MRI: Eighty Percent Reduction in Contrast Dose. Acad Radiol. 2024. PMID: 39592383. doi:10.1016/j.acra.2024.10.026

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。