基于生成对抗网络在18F-FDG PET/CT图像上分割白质高信号
采用WhyperGAN从18F-FDG PET分割白质高信号(WMH)并估计体积,与H-DenseUnet比较,结果显示WhyperGAN在重度组分割和体积估计上表现更优。
要点
- WhyperGAN在WMH体积>60 mL时DSC为0.751,优于H-DenseUnet的0.564。
- 重度组WhyperGAN召回率0.579、平均体积差0.494,均优于H-DenseUnet。
- WhyperGAN估计WMH体积与真实值相关系数在重度、中度、轻度组分别为0.998、0.983、0.908。
核心结论
- WhyperGAN可基于18F-FDG PET/CT自动分割和估计WMH体积,有助于提升FDG PET/CT对认知障碍患者WMH的评估价值。
主要发现
- DSC值与MRI上WMH体积相关,体积>60 mL时WhyperGAN的DSC为0.751,H-DenseUnet为0.564。
- 体积≤60 mL时DSC随体积减小迅速下降,WhyperGAN为0.362,H-DenseUnet为0.237。
- 重度组WhyperGAN召回率最高(0.579 vs. 0.509),平均体积差最低(0.494 vs. 0.941)。
- WhyperGAN估计WMH体积与真实值相关系数在重度、中度、轻度组分别为0.998、0.983、0.908。
关键数值与推荐
- WMH体积>60 mL时WhyperGAN的DSC为0.751,H-DenseUnet为0.564。
- WMH体积≤60 mL时WhyperGAN的DSC为0.362,H-DenseUnet为0.237。
- 重度组WhyperGAN召回率0.579,H-DenseUnet为0.509;平均体积差WhyperGAN为0.494,H-DenseUnet为0.941。
- WhyperGAN体积估计相关系数:重度组r=0.998,中度组r=0.983,轻度组r=0.908。
临床怎么用
- 对于认知障碍患者,可利用WhyperGAN从18F-FDG PET/CT图像自动分割WMH并估计体积,辅助评估脑白质病变。
局限性
- 研究受限于视觉分析。
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
PURPOSE: White matter hyperintensities (WMH) are typically segmented using MRI because WMH are hardly visible on 18F-FDG PET/CT. This retrospective study was conducted to segment WMH and estimate their volumes from 18F-FDG PET with a generative adversarial network (WhyperGAN). METHODS: We selected patients whose interval between MRI and FDG PET/CT scans was within 3 months, from January 2017 to December 2018, and classified them into mild, moderate, and severe groups by following the semiquantitative rating method of Fazekas. For each group, 50 patients were selected, and of them, we randomly selected 35 patients for training and 15 for testing. WMH were automatically segmented from FLAIR MRI with manual adjustment. Patches of WMH were extracted from 18F-FDG PET and segmented MRI. WhyperGAN was compared with H-DenseUnet, a deep learning method widely used for segmentation tasks, for segmentation performance based on the dice similarity coefficient (DSC), recall, and average volume differences (AVD). For volume estimation, the predicted WMH volumes from PET were compared with ground truth volumes. RESULTS: The DSC values were associated with WMH volumes on MRI. For volumes >60 mL, the DSC values were 0.751 for WhyperGAN and 0.564 for H-DenseUnet. For volumes ≤60 mL, the DSC values rapidly decreased as the volume decreased (0.362 for WhyperGAN vs. 0.237 for H-DenseUnet). For recall, WhyperGAN achieved the highest value in the severe group (0.579 for WhyperGAN vs. 0.509 for H-DenseUnet). For AVD, WhyperGAN achieved the lowest score in the severe group (0.494 for WhyperGAN vs. 0.941 for H-DenseUnet). For the WMH volume estimation, WhyperGAN performed better than H-DenseUnet and yielded excellent correlation coefficients (r = 0.998, 0.983, and 0.908 in the severe, moderate, and mild group). CONCLUSIONS: Although limited by visual analysis, the WhyperGAN based can be used to automatically segment and estimate volumes of WMH from 18F-FDG PET/CT. This would increase the usefulness of 18F-FDG PET/CT for the evaluation of WMH in patients with cognitive impairment.
引用
- Oh KT, Kim D, Ye BS, et al. Segmentation of white matter hyperintensities on 18F-FDG PET/CT images with a generative adversarial network. Eur J Nucl Med Mol Imaging. 2021. PMID: 33693968. doi:10.1007/s00259-021-05285-4
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。