Scholarlink

Objective <p>Denoising low-field MR images is often essential to obtain image quality that is adequate for clinical diagnosis while keeping scan time patient-friendly. The recently introduced zero-shot self-supervised approach shows great promise, requiring no prior data collection for training, which is particularly challenging at low-field. Here, this scan-specific denoising approach is adapted to low-field MR data and optimized to accelerate the training process. </p> Material and method <p>We extended the zero-shot noise-as-clean method by modifying the training process to achieve faster training times. The proposed method was compared to BM4D and the recent zero-shot noise2noise methods. Denoising performance was first evaluated quantitatively on high-field data where high SNR images are available, then assessed qualitatively on prospective low-field data (0.1&#xa0;T). Ultimately, we studied the denoising performance with respect to training on portions of the original data matrix as a potential strategy for further training acceleration. </p> Results <p>The proposed method achieved high denoising performance across different SNR levels within a few seconds on a GPU for typical low-field data dimensions. Additionally, training on portion of the data showed potential for further training acceleration.</p> Discussion <p>In the context of low-field MRI, this denoising method shows great potential, as it could be integrated into acquisition workflows relatively seamlessly to improve image quality. Code: <a href="https://github.com/reinaayde7/zs-nac.git">https://github.com/reinaayde7/zs-nac.git.</a></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

Fast zero-shot deep learning-based denoising method for low-field MR images

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月22日

查看全文
  • Reina Ayde,
  • Gabriel Zihlmann,
  • Najat Salameh,
  • Mathieu Sarracanie

摘要

Objective

Denoising low-field MR images is often essential to obtain image quality that is adequate for clinical diagnosis while keeping scan time patient-friendly. The recently introduced zero-shot self-supervised approach shows great promise, requiring no prior data collection for training, which is particularly challenging at low-field. Here, this scan-specific denoising approach is adapted to low-field MR data and optimized to accelerate the training process.

Material and method

We extended the zero-shot noise-as-clean method by modifying the training process to achieve faster training times. The proposed method was compared to BM4D and the recent zero-shot noise2noise methods. Denoising performance was first evaluated quantitatively on high-field data where high SNR images are available, then assessed qualitatively on prospective low-field data (0.1 T). Ultimately, we studied the denoising performance with respect to training on portions of the original data matrix as a potential strategy for further training acceleration.

Results

The proposed method achieved high denoising performance across different SNR levels within a few seconds on a GPU for typical low-field data dimensions. Additionally, training on portion of the data showed potential for further training acceleration.

Discussion

In the context of low-field MRI, this denoising method shows great potential, as it could be integrated into acquisition workflows relatively seamlessly to improve image quality. Code: https://github.com/reinaayde7/zs-nac.git.