文献速递神经外周血管MR

基于三维定量合成MRI无需额外扫描的深度学习生成MRA图像方法

Deep Learning Approach for Generating MRA Images From 3D Quantitative Synthetic MRI Without Additional Scans.
PubMed 文献 · Invest Radiol · 2020-01-01

本研究纳入11名健康志愿者和4例颅内动脉瘤患者,开发深度学习算法从三维合成MRI原始数据生成MRA图像,并与TOF-MRA比较。深度学习MRA的图像质量与TOF-MRA相当,且优于线性组合MRA,眼动脉分支显示低于TOF-MRA,其余颅内动脉分支显示无显著差异。作者认为该算法可能作为颅内动脉瘤筛查工具,无需额外扫描时间。

要点

  • 深度学习MRA图像质量与TOF-MRA相当(4.2±0.7 vs 4.4±0.7,P=0.99)。
  • 眼动脉分支显示深度学习MRA低于TOF-MRA(1.2±0.5 vs 2.3±1.2,P<0.001)。
  • 深度学习MRA的PSNR、SSIM高于线性组合MRA,HFEN低于线性组合MRA。

关键影像表现/征象

  • 深度学习MRA在所有受试者中成功获得。
  • 深度学习MRA的PSNR和SSIM显著高于线性组合MRA,HFEN显著低于线性组合MRA(PSNR 35.3±0.5 vs 34.0±0.5,P<0.001;SSIM 0.93±0.02 vs 0.82±0.02,P<0.001;HFEN 0.61±0.08 vs 0.86±0.05,P<0.001)。
  • 深度学习MRA整体图像质量与TOF-MRA相当(4.2±0.7 vs 4.4±0.7,P=0.99),两者均优于线性组合MRA(1.5±0.6,P<0.001)。
  • 深度学习MRA与TOF-MRA在颅内动脉分支可见性上无显著差异,但眼动脉分支可见性深度学习MRA低于TOF-MRA(1.2±0.5 vs 2.3±1.2,P<0.001)。

诊断标准与关键数值

  • 图像质量评估指标包括峰值信噪比(PSNR)、结构相似性指数(SSIM)和高频误差范数(HFEN),以TOF-MRA为参考计算。
  • 整体图像质量和分支可视化采用5分Likert量表由2名 board-certified 放射科医生盲法独立评分。

临床应用与阅片要点

  • 深度学习MRA可从3D合成MRI原始数据生成,无需额外扫描时间。
  • 作者认为该算法可能作为颅内动脉瘤筛查工具。
  • 眼动脉分支显示深度学习MRA低于TOF-MRA,阅片时需注意。

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: Quantitative synthetic magnetic resonance imaging (MRI) enables synthesis of various contrast-weighted images as well as simultaneous quantification of T1 and T2 relaxation times and proton density. However, to date, it has been challenging to generate magnetic resonance angiography (MRA) images with synthetic MRI. The purpose of this study was to develop a deep learning algorithm to generate MRA images based on 3D synthetic MRI raw data.

MATERIALS AND METHODS: Eleven healthy volunteers and 4 patients with intracranial aneurysms were included in this study. All participants underwent a time-of-flight (TOF) MRA sequence and a 3D-QALAS synthetic MRI sequence. The 3D-QALAS sequence acquires 5 raw images, which were used as the input for a deep learning network. The input was converted to its corresponding MRA images by a combination of a single-convolution and a U-net model with a 5-fold cross-validation, which were then compared with a simple linear combination model. Image quality was evaluated by calculating the peak signal-to-noise ratio (PSNR), structural similarity index measurements (SSIMs), and high frequency error norm (HFEN). These calculations were performed for deep learning MRA (DL-MRA) and linear combination MRA (linear-MR), relative to TOF-MRA, and compared with each other using a nonparametric Wilcoxon signed-rank test. Overall image quality and branch visualization, each scored on a 5-point Likert scale, were blindly and independently rated by 2 board-certified radiologists.

RESULTS: Deep learning MRA was successfully obtained in all subjects. The mean PSNR, SSIM, and HFEN of the DL-MRA were significantly higher, higher, and lower, respectively, than those of the linear-MRA (PSNR, 35.3 ± 0.5 vs 34.0 ± 0.5, P < 0.001; SSIM, 0.93 ± 0.02 vs 0.82 ± 0.02, P < 0.001; HFEN, 0.61 ± 0.08 vs 0.86 ± 0.05, P < 0.001). The overall image quality of the DL-MRA was comparable to that of TOF-MRA (4.2 ± 0.7 vs 4.4 ± 0.7, P = 0.99), and both types of images were superior to that of linear-MRA (1.5 ± 0.6, for both P < 0.001). No significant differences were identified between DL-MRA and TOF-MRA in the branch visibility of intracranial arteries, except for ophthalmic artery (1.2 ± 0.5 vs 2.3 ± 1.2, P < 0.001).

CONCLUSIONS: Magnetic resonance angiography generated by deep learning from 3D synthetic MRI data visualized major intracranial arteries as effectively as TOF-MRA, with inherently aligned quantitative maps and multiple contrast-weighted images. Our proposed algorithm may be useful as a screening tool for intracranial aneurysms without requiring additional scanning time.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Fujita S, Hagiwara A, Otsuka Y, et al. Deep Learning Approach for Generating MRA Images From 3D Quantitative Synthetic MRI Without Additional Scans. Invest Radiol. 2020. PMID: 31977603. doi:10.1097/RLI.0000000000000628

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。