文献速递技术与安全MR

T2加权MRI重采集与深度学习生成对抗网络图像重建的质量比较:多阅片者研究

Quality of T2-weighted MRI re-acquisition versus deep learning GAN image reconstruction: A multi-reader study.
PubMed 文献 · Eur J Radiol · 2023-12-12

本研究评估CycleGAN提升T2加权图像质量的能力,纳入96例因首次扫描质量差(RAD1)而重采集后质量改善(RAD2)的患者共192次扫描。深度学习分类器正确辨别71.9%的质量类别,CycleGAN图像(QI1、QI2)定量评分显著高于原始扫描(p < 0.001),但20例多阅片者研究中CycleGAN未显示定性改善,无阅片者偏好QI2用于诊断。

要点

  • 深度学习分类器对质量类别的辨别正确率为71.9%,其中差质量识别率90.6%(96/106),可诊断质量识别率48.8%(42/86)。
  • CycleGAN图像(QI1、QI2)的深度学习分类器评分始终高于原始扫描(p < 0.001),但多阅片者分析中无定性改善。
  • 多数患者QI2较RAD2整体质量和运动伪影变差,噪声水平相似(8/20),无阅片者偏好QI2用于诊断。

核心结论

  • 尽管CycleGAN在定量指标上有提升,但T2WI的诊断质量、噪声或运动伪影并无定性改善,专家放射科医生不偏好CycleGAN图像,凸显定量与定性指标之间的差距。

研究设计与样本

  • 研究采用CycleGAN算法增强T2WI质量,纳入96例因首次轴向T2WI质量差(RAD1)而重采集后质量改善(RAD2)的患者共192次扫描。
  • CycleGAN算法给出0-1的深度学习分类器评分以量化质量,并分别从RAD1和RAD2生成增强版本QI1和QI2。
  • 选取20例患者子集进行盲法多阅片者研究,四名放射科医生按1-4分评估T2WI质量。
  • 多阅片者研究呈现60对图像(RAD1 vs RAD2、RAD1 vs QI1、RAD2 vs QI2),供选择序列偏好并量化质量变化。

诊断标准与关键数值

  • 深度学习分类器正确辨别71.9%的质量类别,其中差质量识别率90.6%(96/106),可诊断质量识别率48.8%(42/86),对象为原始序列(RAD1、RAD2)。
  • CycleGAN图像(QI1、QI2)的深度学习分类器评分始终高于原始扫描(p < 0.001)。
  • 多阅片者分析中,多数患者QI2较RAD2整体质量和运动变差,噪声水平相似(8/20)。
  • 无阅片者偏好QI2而非RAD2用于诊断。

临床应用与阅片要点

  • 原文未据此给出推荐。

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

PURPOSE: To evaluate CycleGAN's ability to enhance T2-weighted image (T2WI) quality.

METHOD: A CycleGAN algorithm was used to enhance T2WI quality. 96 patients (192 scans) were identified from patients who underwent multiple axial T2WI due to poor quality on the first attempt (RAD1) and improved quality on re-acquisition (RAD2). CycleGAN algorithm gave DL classifier scores (0-1) for quality quantification and produced enhanced versions of QI1 and QI2 from RAD1 and RAD2, respectively. A subset (n = 20 patients) was selected for a blinded, multi-reader study, where four radiologists rated T2WI on a scale of 1-4 for quality. The multi-reader study presented readers with 60 image pairs (RAD1 vs RAD2, RAD1 vs QI1, and RAD2 vs QI2), allowing for selecting sequence preferences and quantifying the quality changes.

RESULTS: The DL classifier correctly discerned 71.9 % of quality classes, with 90.6 % (96/106) as poor quality and 48.8 % (42/86) as diagnostic in original sequences (RAD1, RAD2). CycleGAN images (QI1, QI2) demonstrated quantitative improvements, with consistently higher DL classifier scores than original scans (p < 0.001). In the multi-reader analysis, CycleGAN demonstrated no qualitative improvements, with diminished overall quality and motion in QI2 in most patients compared to RAD2, with noise levels remaining similar (8/20). No readers preferred QI2 to RAD2 for diagnosis.

CONCLUSION: Despite quantitative enhancements with CycleGAN, there was no qualitative boost in T2WI diagnostic quality, noise, or motion. Expert radiologists didn't favor CycleGAN images over standard scans, highlighting the divide between quantitative and qualitative metrics.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Belue MJ, Harmon SA, Masoudi S, et al. Quality of T2-weighted MRI re-acquisition versus deep learning GAN image reconstruction: A multi-reader study. Eur J Radiol. 2023. PMID: 38128256. doi:10.1016/j.ejrad.2023.111259

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。