文献速递骨肌MR

7 T 膝关节加速高分辨率深度学习重建涡轮自旋回波 MRI

Accelerated High-Resolution Deep Learning Reconstruction Turbo Spin Echo MRI of the Knee at 7 T.
PubMed 文献 · Invest Radiol · 2024-07-04

前瞻性单中心研究纳入 23 名健康志愿者,在 7 T 下行膝关节二维涡轮自旋回波采集,比较 2、3、4 倍并行加速下深度学习重建与常规 GRAPPA 算法的图像质量。4 倍加速时深度学习重建在图像对比度、锐利度、噪声和整体质量上均显著优于对应 GRAPPA 重建(P < 0.001),且与 2–3 倍加速 GRAPPA 相比多数指标更优(P ≤ 0.031);深度学习重建各加速倍数间各质量指标无显著差异(P ≥ 0.082)。

要点

  • 4 倍加速深度学习重建图像在对比度、锐利度、噪声及整体质量上显著优于对应 GRAPPA 重建(P < 0.001)。
  • 4 倍加速深度学习图像对比度、锐利度、噪声及整体质量显著优于 2–3 倍 GRAPPA 图像(P ≤ 0.031)。
  • 2、3、4 倍加速深度学习重建之间所有图像质量指标均无显著差异(P ≥ 0.082)。

核心结论

  • 深度学习重建可显著改善 7 T 膝关节 4 倍并行加速高分辨率 TSE 图像的多项质量指标,展示了该技术在加速二维 TSE 采集中的技术潜力。

研究设计与样本

  • 前瞻性单中心研究,纳入 23 名健康志愿者行 7 T 膝关节 MRI。

关键影像表现/征象

  • 采集 2、3、4 倍加速的脂肪抑制质子密度(PD-fs)和 T1 加权冠状位二维 TSE 图像,编码体素体积 0.31 × 0.31 × 1.5 mm³。
  • 每套原始数据分别用深度学习算法和常规 GRAPPA 算法重建。
  • 三名阅片者分别对图像对比度、锐利度、伪影、噪声和整体质量进行评分。
  • 4 倍加速时采集时间:PD-fs 为 4 分 15 秒,T1 为 3 分 9 秒。

诊断标准与关键数值

  • 图像质量由三名阅片者按对比度、锐利度、伪影、噪声、整体质量五项指标评分,采用 Friedman 方差分析和 Wilcoxon 符号秩检验比较。
  • 4 倍加速深度学习重建 vs 对应 GRAPPA 重建:对比度、锐利度、噪声、整体质量均显著更优(P < 0.001)。
  • 4 倍加速深度学习重建 vs 2–3 倍 GRAPPA 重建:对比度、锐利度、噪声、整体质量显著更优(P ≤ 0.031)。
  • PD-fs 2 倍加速 GRAPPA 的图像对比度(P = 0.087)、T1 加权 2 倍加速 GRAPPA 的图像噪声(P = 0.180)及两序列 2–3 倍加速 GRAPPA 的图像伪影(P ≥ 0.102)与 4 倍加速深度学习重建无显著差异。
  • 2、3、4 倍加速深度学习重建之间所有图像质量指标均无显著差异(P ≥ 0.082)。

临床应用与阅片要点

  • 在 7 T 膝关节二维 TSE 采集中,4 倍并行加速结合深度学习重建可在保持图像质量的同时缩短采集时间(PD-fs 4 分 15 秒、T1 3 分 9 秒)。
  • 深度学习重建在 2–4 倍加速下图像质量指标保持稳定,为加速采集提供技术依据。

局限性

  • 本研究为前瞻性单中心研究,仅纳入 23 名健康志愿者。
  • 本研究仅探索深度学习重建在 7 T 膝关节加速二维 TSE 采集中的技术潜力。

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: The aim of this study was to compare the image quality of 7 T turbo spin echo (TSE) knee images acquired with varying factors of parallel-imaging acceleration reconstructed with deep learning (DL)-based and conventional algorithms.

MATERIALS AND METHODS: This was a prospective single-center study. Twenty-three healthy volunteers underwent 7 T knee magnetic resonance imaging. Two-, 3-, and 4-fold accelerated high-resolution fat-signal-suppressing proton density (PD-fs) and T1-weighted coronal 2D TSE acquisitions with an encoded voxel volume of 0.31 × 0.31 × 1.5 mm 3 were acquired. Each set of raw data was reconstructed with a DL-based and a conventional Generalized Autocalibrating Partially Parallel Acquisition (GRAPPA) algorithm. Three readers rated image contrast, sharpness, artifacts, noise, and overall quality. Friedman analysis of variance and the Wilcoxon signed rank test were used for comparison of image quality criteria.

RESULTS: The mean age of the participants was 32.0 ± 8.1 years (15 male, 8 female). Acquisition times at 4-fold acceleration were 4 minutes 15 seconds (PD-fs, Supplemental Video is available at http://links.lww.com/RLI/A938 ) and 3 minutes 9 seconds (T1, Supplemental Video available at http://links.lww.com/RLI/A939 ). At 4-fold acceleration, image contrast, sharpness, noise, and overall quality of images reconstructed with the DL-based algorithm were significantly better rated than the corresponding GRAPPA reconstructions ( P < 0.001). Four-fold accelerated DL-reconstructed images scored significantly better than 2- to 3-fold GRAPPA-reconstructed images with regards to image contrast, sharpness, noise, and overall quality ( P ≤ 0.031). Image contrast of PD-fs images at 2-fold acceleration ( P = 0.087), image noise of T1-weighted images at 2-fold acceleration ( P = 0.180), and image artifacts for both sequences at 2- and 3-fold acceleration ( P ≥ 0.102) of GRAPPA reconstructions were not rated differently than those of 4-fold accelerated DL-reconstructed images. Furthermore, no significant difference was observed for all image quality measures among 2-fold, 3-fold, and 4-fold accelerated DL reconstructions ( P ≥ 0.082).

CONCLUSIONS: This study explored the technical potential of DL-based image reconstruction in accelerated 2D TSE acquisitions of the knee at 7 T. DL reconstruction significantly improved a variety of image quality measures of high-resolution TSE images acquired with a 4-fold parallel-imaging acceleration compared with a conventional reconstruction algorithm.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Marth AA, von Deuster C, Sommer S, et al. Accelerated High-Resolution Deep Learning Reconstruction Turbo Spin Echo MRI of the Knee at 7 T. Invest Radiol. 2024. PMID: 38960863. doi:10.1097/RLI.0000000000001095

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。