文献速递技术与安全CTMRPET

生成对抗网络在医学影像辐射降低与伪影校正中的作用

The Role of Generative Adversarial Networks in Radiation Reduction and Artifact Correction in Medical Imaging.
PubMed 文献 · J Am Coll Radiol · 2019-01-01

生成对抗网络是基于示例图像训练的深度学习技术,在放射学中具有独特优势。本文概述了生成对抗网络及其在医学影像研究中的应用,包括通过减少伪影导致的重复扫描、缩短采集时间、从低剂量或无剂量检查生成更高质量图像来降低患者辐射暴露。

要点

  • 生成对抗网络可减少伪影导致的重复扫描,从而降低辐射暴露
  • 生成对抗网络能从低剂量或无剂量检查生成更高质量图像
  • 生成对抗网络可缩短采集时间,助力降低辐射剂量

核心结论

  • 生成对抗网络在放射学中具有独特优势,可能降低患者辐射暴露并提升图像质量。

研究设计与样本

  • 本文为综述,概述生成对抗网络及其在当前医学影像研究中的应用;原文未报告检索范围、纳入文献数量及证据分级。

局限性

  • 原文未报告局限性。

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

Adversarial networks were developed to complete powerful image-processing tasks on the basis of example images provided to train the networks. These networks are relatively new in the field of deep learning and have proved to have unique strengths that can potentially benefit radiology. Specifically, adversarial networks have the potential to decrease radiation exposure to patients through minimizing repeat imaging due to artifact, decreasing acquisition time, and generating higher quality images from low-dose or no-dose studies. The authors provide an overview of a specific type of adversarial network called a "generalized adversarial network" and review its uses in current medical imaging research.

来源:J Am Coll Radiol,查看原文。版权归原作者所有。

引用

  1. Vey BL, Gichoya JW, Prater A, et al. The Role of Generative Adversarial Networks in Radiation Reduction and Artifact Correction in Medical Imaging. J Am Coll Radiol. 2019. PMID: 31492405. doi:10.1016/j.jacr.2019.05.040

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。