文献速递神经MR

基于生成对抗网络的对比增强:合成对比脑磁共振成像

Generative Adversarial Network Based Contrast Enhancement: Synthetic Contrast Brain Magnetic Resonance Imaging.
PubMed 文献 · Acad Radiol · 2024-12-18

研究使用CycleGAN模型对81名参与者的脑MRI进行虚拟对比增强,生成合成对比增强T1加权图像;测试集MSE为0.0038、SSIM为0.58,最优子模型MSE为0.0053、SSIM为0.8;四名放射科医师的视觉图灵测试验证了定性表现,结论支持该模型生成合成对比增强脑MR图像的效能。

要点

  • CycleGAN可基于平扫T1加权图像生成合成对比增强图像,测试集MSE为0.0038、SSIM为0.58。
  • 最优子模型达到MSE为0.0053、SSIM为0.8。
  • 四名不同临床经验放射科医师的视觉图灵测试验证了合成图像的定性表现。

核心结论

  • 研究结果支持CycleGAN模型生成合成对比增强T1加权脑MR图像的效能,定量与定性评价均显示良好表现,该方法有望可能消除静脉对比剂的需求从而降低相关风险。

研究设计与样本

  • 研究纳入81名参与者(54名女性、27名男性;平均年龄35岁,范围19-68岁),在3.0特斯拉MRI扫描仪上采集10,235幅图像。
  • 采集T1加权及给予标准剂量钆基对比剂后的对比增强图像,训练CycleGAN模型处理增强前后图像以生成合成对比增强T1加权图像。
  • 数据集按80%训练、10%验证、10%测试划分,使用TensorBoard防止训练过程中图像退化。
  • 四名不同临床经验的放射科医师参与视觉图灵测试,在平扫输入图像对应的真实对比增强图像与CycleGAN合成图像之间进行选择。

诊断标准与关键数值

  • 测试集全数据集:均方误差(MSE)为0.0038,结构相似性指数(SSIM)为0.58。
  • 子模型中最成功模型:MSE为0.0053,SSIM为0.8。
  • 定性评价通过四名不同临床经验放射科医师的视觉图灵测试验证。

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: Magnetic resonance imaging (MRI) is a vital tool for diagnosing neurological disorders, frequently utilising gadolinium-based contrast agents (GBCAs) to enhance resolution and specificity. However, GBCAs present certain risks, including side effects, increased costs, and repeated exposure. This study proposes an innovative approach using generative adversarial networks (GANs) for virtual contrast enhancement in brain MRI, with the aim of reducing or eliminating GBCAs, minimising associated risks, and enhancing imaging efficiency while preserving diagnostic quality.

MATERIAL AND METHODS: In this study, 10,235 images were acquired in a 3.0 Tesla MRI scanner from 81 participants (54 females, 27 males; mean age 35 years, range 19-68 years). T1-weighted and contrast-enhanced images were obtained following the administration of a standard dose of a GBCA. In order to generate "synthetic" images for contrast-enhanced T1-weighted, a CycleGAN model, a sub-model of the GAN structure, was trained to process pre- and post-contrast images. The dataset was divided into three subsets: 80% for training, 10% for validation, and 10% for testing. TensorBoard was employed to prevent image deterioration throughout the training phase, and the image processing and training procedures were optimised. The radiologists were presented with a non-contrast input image and asked to choose between a real contrast-enhanced image and synthetic MR images generated by CycleGAN corresponding to this non-contrast MR image (Turing test).

RESULTS: The performance of the CycleGAN model was evaluated using a combination of quantitative and qualitative analyses. For the entire dataset, in the test set, the mean square error (MSE) was 0.0038, while the structural similarity index (SSIM) was 0.58. Among the submodels, the most successful model achieved an MSE of 0.0053, while the SSIM was 0.8. The qualitative evaluation was validated through a visual Turing test conducted by four radiologists with varying levels of clinical experience.

CONCLUSION: The findings of this study support the efficacy of the CycleGAN model in generating synthetic contrast-enhanced T1-weighted brain MR images. Both quantitative and qualitative evaluations demonstrated excellent performance, confirming the model's ability to produce realistic synthetic images. This method shows promise in potentially eliminating the need for intravenous contrast agents, thereby minimising the associated risks of their use.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Solak M, Tören M, Asan B, et al. Generative Adversarial Network Based Contrast Enhancement: Synthetic Contrast Brain Magnetic Resonance Imaging. Acad Radiol. 2024. PMID: 39694785. doi:10.1016/j.acra.2024.11.021

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。