Scholarlink

This study challenges the validity of retrospective undersampling in MRI data science by analysis via an MRI physics simulation. We demonstrate that retrospective undersampling, a method often used to create training data for reconstruction models, can inherently alter MRI signals from their prospective counterparts. This arises from the sequential nature of MRI acquisition, where undersampling post-acquisition effectively alters the MR sequence and the magnetization dynamic in a non-linear fashion.

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

Abstract: Death by Retrospective Undersampling

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Junaid R. Rajput,
  • Simon Weinmueller,
  • Jonathan Endres,
  • Peter Dawood,
  • Florian Knoll,
  • Andreas Maier,
  • Moritz Zaiss

摘要

This study challenges the validity of retrospective undersampling in MRI data science by analysis via an MRI physics simulation. We demonstrate that retrospective undersampling, a method often used to create training data for reconstruction models, can inherently alter MRI signals from their prospective counterparts. This arises from the sequential nature of MRI acquisition, where undersampling post-acquisition effectively alters the MR sequence and the magnetization dynamic in a non-linear fashion.