文献速递神经外周血管MR

MR-self Noise2Noise:自监督深度学习提升亚毫米3D MR图像质量

MR-self Noise2Noise: self-supervised deep learning-based image quality improvement of submillimeter resolution 3D MR images.
PubMed 文献 · Eur Radiol · 2022-11-15

本研究开发仅利用常规临床扫描的自监督深度学习去噪网络,在185例MP-RAGE及18例血管壁成像上评估。结果显示DNN在图像质量、细结构显示和病灶清晰度上均优于常规图像,定量误差更小且体积测量相当或更优,并在不同序列参数上展现泛化潜力。

要点

  • 自监督DNN可提升3D高分辨率MR图像质量与病灶清晰度
  • 定量误差优于常规图像,体积测量相当或更优
  • 在不同脉冲序列的VWI上同样改善图像质量,具泛化潜力

关键影像表现/征象

  • DNN处理后的MP-RAGE在图像质量、细结构描绘和病灶清晰度上均优于常规MP-RAGE。
  • DNN在不同模拟噪声水平下定量误差指标更优,体积测量结果相当或更优。
  • DNN应用于脉冲序列和参数不同的VWI数据时图像质量同样改善。

诊断标准与关键数值

  • 定性评估显示DNN图像质量平均评分在MP-RAGE为4.9 vs 常规3.7(p<0.001),VWI为4.6 vs 3.5(p<0.001)。
  • 定量评估中DNN误差指标优于常规方法(p<0.001),体积测量相当(p>0.09)或更优(p<0.02)。

临床应用与阅片要点

  • 该自监督去噪方法可直接利用常规临床扫描训练,无需额外采集噪声标签。
  • 阅片时DNN处理后的MP-RAGE可能提升细结构和病灶的显示,但需注意其基于自监督训练,定性评估样本量有限。
  • 在VWI等不同序列参数上也观察到图像质量改善,提示可推广至多种临床MRI。

局限性

  • 回顾性研究设计。
  • 定性评估样本量较小(20例MP-RAGE,18例VWI)。
  • 定量评估基于模拟噪声水平,非真实噪声环境。

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 study aimed to develop a deep neural network (DNN)-based noise reduction and image quality improvement by only using routine clinical scans and evaluate its performance in 3D high-resolution MRI.

METHODS: This retrospective study included T1-weighted magnetization-prepared rapid gradient-echo (MP-RAGE) images from 185 clinical scans: 135 for DNN training, 11 for DNN validation, 20 for qualitative evaluation, and 19 for quantitative evaluation. Additionally, 18 vessel wall imaging (VWI) data were included to evaluate generalization. In each scan of the DNN training set, two noise-independent images were generated from the k-space data, resulting in an input-label pair. 2.5D U-net architecture was utilized for the DNN model. Qualitative evaluation between conventional MP-RAGE and DNN-based MP-RAGE was performed by two radiologists in image quality, fine structure delineation, and lesion conspicuity. Quantitative evaluation was performed with full sampled data as a reference by measuring quantitative error metrics and volumetry at 7 different simulated noise levels. DNN application on VWI was evaluated by two radiologists in image quality.

RESULTS: Our DNN-based MP-RAGE outperformed conventional MP-RAGE in all image quality parameters (average scores = 3.7 vs. 4.9, p < 0.001). In the quantitative evaluation, DNN showed better error metrics (p < 0.001) and comparable (p > 0.09) or better (p < 0.02) volumetry results than conventional MP-RAGE. DNN application to VWI also revealed improved image quality (3.5 vs. 4.6, p < 0.001).

CONCLUSION: The proposed DNN model successfully denoises 3D MR image and improves its image quality by using routine clinical scans only.

KEY POINTS: • Our deep learning framework successfully improved conventional 3D high-resolution MRI in all image quality parameters, fine structure delineation, and lesion conspicuity. • Compared to conventional MRI, the proposed deep neural network-based MRI revealed better quantitative error metrics and comparable or better volumetry results. • Deep neural network application to 3D MRI whose pulse sequences and parameters were different from the training data showed improvement in image quality, revealing the potential to generalize on various clinical MRI.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Jung, Lee, Seo, et al. MR-self Noise2Noise: self-supervised deep learning-based image quality improvement of submillimeter resolution 3D MR images. Eur Radiol. 2022. PMID: 36378250. doi:10.1007/s00330-022-09243-y

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。