文献速递骨肌MR

利用开源深度学习模型生成膝关节合成T2*加权梯度回波图像

Generating Synthetic T2*-Weighted Gradient Echo Images of the Knee with an Open-source Deep Learning Model.
PubMed 文献 · Acad Radiol · 2025-04-02

本研究旨在开发开源深度学习模型,利用脂肪抑制中间加权图像生成膝关节合成T2*W图像。采用cycleGAN模型以12,118幅矢状位膝关节MR图像训练,并在独立测试集2,996幅图像上验证。合成图像与常规图像在各项诊断发现上具有互换性(组内相关系数>0.95),图像质量指标中位NRMSE、PSNR和SSIM分别为0.5、17.4和0.5,识别出的伪影对诊断无影响或影响轻微。

要点

  • 合成T2*W图像与常规图像在软骨、滑膜含铁血黄素沉积、软骨钙化及骺板评估等发现上具有互换性(ICC>0.95)。
  • 合成图像与常规图像的平均体素强度相等,四种组织Bland-Altman分析结果一致。
  • 识别出四种伪影(几何变形86/163例、物体插入/遗漏11/163例、类卷褶伪影26/163例、不完全脂肪抑制120/163例),对诊断影响中位数为0(无影响)。

核心结论

  • 所开发的开源GAN模型生成的膝关节合成T2*W图像具有高诊断价值和质量,识别出的伪影对图像诊断价值无影响或影响轻微。

研究设计与样本

  • 采用cycleGAN模型,以12,118幅矢状位膝关节MR图像训练,并在独立测试集2,996幅图像上测试;评估合成T2*W图像与一系列诊断发现的互换性,采用Bland-Altman图评估四种组织的体素强度,并使用NRMSE、SSIM和PSNR评估图像质量;代码、模型和独立可执行文件已在github提供。

关键影像表现/征象

  • 合成T2*W图像可用于评估软骨、滑膜含铁血黄素沉积(滑膜blooming)、软骨钙化以及儿童骺板。
  • 识别出四种伪影:几何变形(86/163例)、物体插入/遗漏(11/163例)、类卷褶伪影(26/163例)和不完全脂肪抑制(120/163例),对诊断影响的中位数为0(无影响)。

诊断标准与关键数值

  • 合成T2*W图像与常规图像对所有诊断发现的组内相关系数>0.95,判定为可互换。
  • 图像质量中位NRMSE为0.5,PSNR为17.4,SSIM为0.5。
  • 合成图像与常规图像的平均体素强度相等。

临床应用与阅片要点

  • 该模型可利用常规脂肪抑制中间加权图像生成合成T2*W图像,用于需要T2*W对比的临床场景(如软骨、滑膜含铁血黄素沉积、软骨钙化和儿童骺板评估)。
  • 阅片时需注意合成图像可能出现的几何变形、物体插入/遗漏、类卷褶伪影和不完全脂肪抑制,但原文报告这些伪影对诊断无影响或影响轻微。
  • 代码、模型和独立可执行文件已在github开源提供,便于重复和临床转化。

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

RATIONALE AND OBJECTIVES: Routine knee MRI protocols for 1.5 T and 3 T scanners, do not include T2*-w gradient echo (T2*W) images, which are useful in several clinical scenarios such as the assessment of cartilage, synovial blooming (deposition of hemosiderin), chondrocalcinosis and the evaluation of the physis in pediatric patients. Herein, we aimed to develop an open-source deep learning model that creates synthetic T2*W images of the knee using fat-suppressed intermediate-weighted images.

MATERIALS AND METHODS: A cycleGAN model was trained with 12,118 sagittal knee MR images and tested on an independent set of 2996 images. Diagnostic interchangeability of synthetic T2*W images was assessed against a series of findings. Voxel intensity of four tissues was evaluated with Bland-Altman plots. Image quality was assessed with the use of root mean squared error (NRMSE), structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). Code, model and a standalone executable file are provided on github.

RESULTS: The model achieved a median NRMSE, PSNR and SSIM of 0.5, 17.4, and 0.5, respectively. Images were found interchangeable with an intraclass correlation coefficient >0.95 for all findings. Mean voxel intensity was equal between synthetic and conventional images. Four types of artifacts were identified: geometrical distortion (86/163 cases), object insertion/omission (11/163 cases), a wrap-around-like (26/163 cases) and an incomplete fat-suppression artifact (120/163 cases), which had a median 0 impact (no impact) on the diagnosis.

CONCLUSION: In conclusion, the developed open-source GAN model creates synthetic T2*W images of the knee of high diagnostic value and quality. The identified artifacts had no or minor effect on the diagnostic value of the images.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Vrettos K, Vassalou EE, Vamvakerou G, et al. Generating Synthetic T2*-Weighted Gradient Echo Images of the Knee with an Open-source Deep Learning Model. Acad Radiol. 2025. PMID: 40175204. doi:10.1016/j.acra.2025.03.015

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。