文献速递神经核医学肿瘤 PET/CT

通过空间归一化方法改进18F-FDG PET定量

Improving 18F-FDG PET Quantification Through a Spatial Normalization Method.
PubMed 文献 · J Nucl Med · 2024-10-01

本研究提出一种迁移学习方法,将预训练的淀粉样蛋白PET深度神经网络模型微调后用于18F-FDG脑PET的空间归一化,无需三维MRI。仅用103例18F-FDG PET和MR图像训练,在65例内部和78例外部队列测试。所提方法在归一化互信息和SUV比相关性上优于统计参数图,且外部队列跨种族、扫描仪和重建算法仍表现良好。

要点

  • 迁移学习可从淀粉样蛋白PET模型微调出18F-FDG PET空间归一化模型,无需三维MRI。
  • 所提方法在内部和外部队列中SUV比相关性和组内相关系数均高于统计参数图。
  • 外部队列使用不同PET扫描仪和重建算法仍保持良好相关性,显示泛化潜力。

核心结论

  • 本研究成功将迁移学习应用于深度神经网络进行18F-FDG PET空间归一化,证明其资源高效且性能改进。

研究设计与样本

  • 基于深度学习模型的自动空间归一化方法,用仅103例18F-FDG PET和MR图像对预训练淀粉样蛋白PET模型进行微调。
  • 训练后在65例内部测试集和78例外部测试集上测试。
  • 所有1 mm各向同性体素T1 MR图像经FreeSurfer处理提供皮层分割图,以小脑灰质为参考区提取地面真值区域SUV比。

主要发现

  • 所提方法较统计参数图显示更优空间归一化,表现为归一化互信息增加及PET图像大小和形状匹配更好。
  • 定量评估显示所提方法在内部和外部数据集多个脑区均具有持续更高的SUV比相关性和组内相关系数。
  • 外部队列因不同种族分布、不同PET扫描仪和图像重建算法,其良好相关性和组内相关系数值值得注意。

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)。

原文

Quantification of 18F-FDG PET images is useful for accurate diagnosis and evaluation of various brain diseases, including brain tumors, epilepsy, dementia, and Parkinson disease. However, accurate quantification of 18F-FDG PET images requires matched 3-dimensional T1 MRI scans of the same individuals to provide detailed information on brain anatomy. In this paper, we propose a transfer learning approach to adapt a pretrained deep neural network model from amyloid PET to spatially normalize 18F-FDG PET images without the need for 3-dimensional MRI. Methods: The proposed method is based on a deep learning model for automatic spatial normalization of 18F-FDG brain PET images, which was developed by fine-tuning a pretrained model for amyloid PET using only 103 18F-FDG PET and MR images. After training, the algorithm was tested on 65 internal and 78 external test sets. All T1 MR images with a 1-mm isotropic voxel size were processed with FreeSurfer software to provide cortical segmentation maps used to extract a ground-truth regional SUV ratio using cerebellar gray matter as a reference region. These values were compared with those from spatial normalization-based quantification methods using the proposed method and statistical parametric mapping software. Results: The proposed method showed superior spatial normalization compared with statistical parametric mapping, as evidenced by increased normalized mutual information and better size and shape matching in PET images. Quantitative evaluation revealed a consistently higher SUV ratio correlation and intraclass correlation coefficients for the proposed method across various brain regions in both internal and external datasets. The remarkably good correlation and intraclass correlation coefficient values of the proposed method for the external dataset are noteworthy, considering the dataset's different ethnic distribution and the use of different PET scanners and image reconstruction algorithms. Conclusion: This study successfully applied transfer learning to a deep neural network for 18F-FDG PET spatial normalization, demonstrating its resource efficiency and improved performance. This highlights the efficacy of transfer learning, which requires a smaller number of datasets than does the original network training, thus increasing the potential for broader use of deep learning-based brain PET spatial normalization techniques for various clinical and research radiotracers.

来源:J Nucl Med,查看原文。版权归原作者所有。

引用

  1. Kim D, Kang SK, Shin SA, et al. Improving 18F-FDG PET Quantification Through a Spatial Normalization Method. J Nucl Med. 2024. PMID: 39209545. doi:10.2967/jnumed.123.267360

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。