文献速递神经技术与安全MR

深度学习重建加速脑MRI对异常征象的高加速失真风险

The Challenge of Rendering Abnormalities Accurately Using Deep Learning-Based Reconstruction in Accelerated Brain MRI: A Disproportionate Loss of Clinically Relevant Image Information at Higher Rates of Acceleration.
PubMed 文献 · Invest Radiol · 2026-09-14

本研究基于fastMRI及fastMRI+中5847例脑MRI原始k空间数据,回顾性模拟2至12倍欠采样并用端到端变分网络重建。结果显示,4倍以上加速时,异常区域内NMSE升高和PSNR、SSIM下降均较正常区域更明显。提示高加速深度学习重建可能不成比例丢失病变相关图像信息。

要点

  • 高于4倍加速时,异常区域图像质量下降明显快于正常区域。
  • 阅片时对高加速深度学习重建图像应警惕病变被平滑或丢失。
  • 异常区域NMSE对加速相关失真最敏感,可作为质控参考指标。

核心结论

  • 深度学习重建脑MRI在较高加速倍数下会发生不成比例且集中于病变区域的图像质量下降。
  • 高于4倍加速时异常区域NMSE随加速倍数升高而更明显增加。
  • 异常区域PSNR和SSIM随加速倍数升高较正常区域下降更快。
  • 区域与加速倍数的交互作用在slice级和bounding-box级3个指标上均有统计学意义。

研究设计与样本

  • 回顾性研究,使用fastMRI中5847例脑MRI检查的原始k空间数据。
  • 其中fastMRI+放射科医师标注的1001例作为测试集,3715例用于训练,1131例用于验证。
  • 图像按2至12倍加速因子回顾性欠采样,并用端到端变分网络重建。
  • 在异常标注包围盒、大小匹配正常对照区域及slice级计算NMSE、SSIM和PSNR。
  • 采用含个体随机截距的线性混合效应模型检验区域与加速倍数的交互作用。

关键影像表现/征象

  • 所有指标在slice级和包围盒级均显示图像质量随加速倍数增加而渐进下降。
  • 低加速倍数下,异常包围盒与正常区域的图像质量相当。
  • 高于4倍加速时,异常区域内NMSE随加速增加较正常区域更明显升高。
  • 高于4倍加速时,异常区域内PSNR和SSIM较正常区域下降显著更快。
  • 这种非对称信息丢失在NMSE上于较高加速倍数时尤为明显。

诊断标准与关键数值

  • 异常与正常区域比较的NMSE、SSIM和PSNR差异及变化趋势见原文结果。
  • 区域与加速倍数交互作用在3个指标、2个分析水平上均调整后P<0.001。

临床应用与阅片要点

  • 使用高加速深度学习重建脑MRI时,应重点核对既往异常区域有无平滑、变形或遗漏。
  • 报告系统重建条件时建议注明加速倍数和重建方式,以便临床判断征象可靠性。
  • 对4倍以上加速图像中的小病灶、边界模糊病变应更保守判读或建议常规序列复查。

局限性

  • 研究为回顾性欠采样模拟,未直接对前瞻性加速采集图像进行验证。
  • 异常区域分析基于放射科医师标注的包围盒,可能包含周围正常组织。
  • 具体图像质量下降分数与真实影像征象可检出性之间的关系原文未进一步量化。

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: Deep learning (DL)-based reconstruction methods can substantially accelerate MRI acquisition while preserving image quality relative to traditional techniques. However, concerns remain regarding their ability to accurately reconstruct abnormalities at higher acceleration factors. This study quantitatively assesses the impact of higher-order acceleration on image quality in DL-reconstructed brain MRI in normal and abnormal cases, emphasizing the utmost need to render abnormal findings accurately.

MATERIALS AND METHODS: Raw k-space image data from 5847 brain MRI examinations (fastMRI) were used. A radiologist-annotated subset of 1001 examinations (fastMRI+) served as the test set; the remainder were split into training (n=3715) and validation (n=1131) sets. Images were retrospectively undersampled (acceleration factors 2 to 12) and reconstructed using an end-to-end variational network. Image quality metrics, including normalized mean squared error (NMSE), structural similarity index measure (SSIM), and peak signal-to-noise ratio (PSNR), were computed within bounding-box annotations containing abnormalities and in size-matched normal control regions, and at the slice-level. The region-by-acceleration interaction was tested using linear mixed-effects models with a subject-level random intercept.

RESULTS: All metrics demonstrated progressive degradation with increasing acceleration across slice-level and bounding-box-level analyses. At lower acceleration rates, bounding boxes with and without abnormalities showed comparable image quality. However, above 4-fold acceleration, NMSE within abnormal regions exhibited a notably sharper increase with rising acceleration compared to normal regions, while abnormal regions demonstrated a significantly faster decline in PSNR and SSIM. This nonsymmetric information loss was particularly evident for NMSE at higher acceleration rates. The region-by-acceleration interaction was statistically significant for all 3 metrics at both levels (all adjusted P<0.001), with the effect largest and most consistent for NMSE.

CONCLUSIONS: Our findings demonstrate a disproportionate, pathology-localized degradation of reconstruction quality as acceleration increases. This emphasizes the importance of rigorous clinical assessment of image quality in DL-MRI reconstruction, particularly at higher undersampling rates, highlighting the need for reconstruction strategies tailored to maintaining diagnostically critical features.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Chen, Johnson, Lui, et al. The Challenge of Rendering Abnormalities Accurately Using Deep Learning-Based Reconstruction in Accelerated Brain MRI: A Disproportionate Loss of Clinically Relevant Image Information at Higher Rates of Acceleration. Invest Radiol. 2026. PMID: 42733315. doi:10.1097/RLI.0000000000001308

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。