Scholarlink

<p>Minimizing acquisition time and motion-artifacts remains challenging in magnetic resonance imaging (MRI) with demands on high-resolution images for accurate diagnosis and treatment. Deep learning-based image restoration offers promising solution by generating high-resolution and artifact-free MR images from low-resolution or motion-corrupted data. To facilitate practical deployment in clinical workflows, this study presents a time-/GPU-efficient framework using 2D network (TS-RCAN) for pseudo-3D MRI super-resolution reconstruction (SRR) and motion-artifact reduction (MAR). Optimal down-sampling factors were identified to balance SRR accuracy and acquisition time. MAR training used a standardized method to induce controllable motion-artifacts of varying severity. Network performance was benchmarked against state-of-the-art 3D networks. Results showed the down-sampling factor <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(1\times 1\times 2\)</EquationSource> </InlineEquation> for <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\times 2\)</EquationSource> </InlineEquation> acceleration and <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(2\times 2\times 2\)</EquationSource> </InlineEquation> for <InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(\times 4\)</EquationSource> </InlineEquation> acceleration achieved optimal SRR performance. TS-RCAN outperformed most 3D networks by &gt; 0.01/1.5&#xa0;dB in SSIM/PSNR while reducing GPU load and inference time by up to 90%. For MAR, TS-RCAN exceeded UNet by up to 0.014/1.48&#xa0;dB in SSIM/PSNR. Additionally, uncertainty estimation correlated with image quality metrics, enabling accuracy prediction without ground truth. TS-RCAN provides an efficient, accurate framework for SRR and MAR with practical relevance to clinical MRI, and offers a flexible basis for future extension to other imaging contrasts and pathological cases.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Performance of a GPU- and time-efficient pseudo-3D network for magnetic resonance image super-resolution and motion artifact reduction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月21日

查看全文
  • Hao Li,
  • Jianan Liu,
  • Marianne Schell,
  • Tao Huang,
  • Arne Lauer,
  • Katharina Schregel,
  • Jessica Jesser,
  • Dominik F. Vollherbst,
  • Martin Bendszus,
  • Sabine Heiland,
  • Tim Hilgenfeld

摘要

Minimizing acquisition time and motion-artifacts remains challenging in magnetic resonance imaging (MRI) with demands on high-resolution images for accurate diagnosis and treatment. Deep learning-based image restoration offers promising solution by generating high-resolution and artifact-free MR images from low-resolution or motion-corrupted data. To facilitate practical deployment in clinical workflows, this study presents a time-/GPU-efficient framework using 2D network (TS-RCAN) for pseudo-3D MRI super-resolution reconstruction (SRR) and motion-artifact reduction (MAR). Optimal down-sampling factors were identified to balance SRR accuracy and acquisition time. MAR training used a standardized method to induce controllable motion-artifacts of varying severity. Network performance was benchmarked against state-of-the-art 3D networks. Results showed the down-sampling factor \(1\times 1\times 2\) for \(\times 2\) acceleration and \(2\times 2\times 2\) for \(\times 4\) acceleration achieved optimal SRR performance. TS-RCAN outperformed most 3D networks by > 0.01/1.5 dB in SSIM/PSNR while reducing GPU load and inference time by up to 90%. For MAR, TS-RCAN exceeded UNet by up to 0.014/1.48 dB in SSIM/PSNR. Additionally, uncertainty estimation correlated with image quality metrics, enabling accuracy prediction without ground truth. TS-RCAN provides an efficient, accurate framework for SRR and MAR with practical relevance to clinical MRI, and offers a flexible basis for future extension to other imaging contrasts and pathological cases.