文献速递骨肌神经MR

基于T1和T2加权脊柱图像深度学习生成的Synth-STIR图像与标准STIR的诊断互换性

Diagnostic interchangeability of deep-learning based Synth-STIR images generated from T1 and T2 weighted spine images.
PubMed 文献 · Eur Radiol · 2025-07-18

这项前瞻性研究纳入199名参与者,比较深度学习生成的Synth-STIR与标准STIR的图像质量和诊断互换性。Synth-STIR扫描时间缩短约180秒,信噪比和对比噪声比显著更高(p<0.001),个体等效指数小于1.61%,主要脊柱病变特征频率无显著差异(p=0.211-1)。结论认为Synth-STIR与标准STIR诊断可互换,可在不牺牲诊断价值的前提下提高脊柱MRI效率。

要点

  • Synth-STIR较标准STIR扫描时间缩短约180秒,信噪比和对比噪声比显著更高(p<0.001)。
  • Synth-STIR与标准STIR对脊柱主要病变特征的报告频率无显著差异(p=0.211-1),个体等效指数小于1.61%。
  • 四位盲法阅片医生对Synth-STIR在伪影、噪声、锐利度和诊断信心方面均评价显著优于标准STIR(均p<0.001)。

核心结论

  • Synth-STIR的信噪比和对比噪声比显著高于标准STIR,与标准STIR诊断可互换,且整体成像时间大幅缩短,可在不牺牲诊断价值的情况下提高效率。

研究设计与样本

  • 前瞻性研究,于2023年7月至2023年8月招募参与者,共纳入199名参与者(106名男性,平均年龄46.8±16.9岁);参与者接受T1WI和T2WI扫描后生成Synth-STIR;由四名独立盲法放射科医生进行主观质量和病变特征评估;采用Wilcoxon检验比较信噪比、对比噪声比和主观图像质量,使用个体等效指数(IEI)检验诊断互换性,计算阅片者间和阅片者内一致性,并进行McNemar检验。

关键影像表现/征象

  • Synth-STIR较标准STIR扫描时间缩短约180秒。
  • Synth-STIR的信噪比和对比噪声比显著高于标准STIR(p<0.001)。
  • 所有阅片者一致认为Synth-STIR在伪影、噪声、锐利度和诊断信心方面显著优于标准STIR(均p<0.001)。

诊断标准与关键数值

  • 个体等效指数(IEI)小于1.61%。
  • Kappa和Kendall一致性范围为0.52-0.97,呈中度至优秀一致性。
  • 标准STIR与Synth-STIR报告的主要脊柱病变特征频率无显著差异(p=0.211-1)。

临床应用与阅片要点

  • Synth-STIR与标准STIR在检测脊柱异常方面诊断可互换,可考虑用于减少脊柱MRI协议扫描时间。
  • Synth-STIR在伪影、噪声、锐利度和诊断信心方面均优于标准STIR,阅片时可参考其图像质量优势。

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

OBJECTIVES: To evaluate image quality and diagnostic interchangeability of synth short-tau inversion recovery (STIR) generated by deep learning in comparison with standard STIR.

MATERIALS AND METHODS: This prospective study recruited participants between July 2023 and August 2023. Participants were scanned with T1WI and T2WI, then generated Synth-STIR. Signal-to-noise ratios (SNR), contrast-to-noise ratios (CNR) were calculated for quantitative evaluation. Four independent, blinded radiologists performed subjective quality and lesion characteristic assessment. Wilcoxon tests were used to assess the differences in SNR, CNR, and subjective image quality. Various diagnostic findings pertinent to the spine were tested for interchangeability using the individual equivalence index (IEI). Inter-reader and intra-reader agreement and concordance were computed, and McNemar tests were performed for comprehensive evaluation.

RESULTS: One hundred ninety-nine participants (106 male patients, mean age 46.8 ± 16.9 years) were included. Compared to standard-STIR, Synth-STIR reduces sequence scanning time by approximately 180 s, has significantly higher SNR and CNR (p < 0.001). For artifacts, noise, sharpness, and diagnostic confidence, all readers agreed that Synth-STIR was significantly better than standard-STIR (all p < 0.001). In addition, the IEI was less than 1.61%. Kappa and Kendall showed a moderate to excellent agreement in the range of 0.52-0.97. There was no significant difference in the frequencies of the major features as reported with standard-STIR and Synth-STIR (p = 0.211-1).

CONCLUSION: Synth-STIR shows significantly higher SNR and CNR, and is diagnostically interchangeable with standard-STIR with a substantial overall reduction in the imaging time, thereby improving efficiency without sacrificing diagnostic value.

KEY POINTS: Question Can generating STIR improve image quality while reducing spine MRI acquisition time in order to increase clinical spine MRI throughput? Findings With reduced acquisition time, Synth-STIR has significantly higher SNR and CNR than standard-STIR and can be interchangeably diagnosed with standard-STIR in detecting spinal abnormalities. Clinical relevance Our Synth-STIR provides the same high-quality images for clinical diagnosis as standard-STIR, while reducing scanning time for spine MRI protocols. Increase clinical spine MRI throughput.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Li J, Xu M, Jiang B, et al. Diagnostic interchangeability of deep-learning based Synth-STIR images generated from T1 and T2 weighted spine images. Eur Radiol. 2025. PMID: 40681776. doi:10.1007/s00330-025-11827-3

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。