基于2-[18F]FDG PET的深度学习淀粉样蛋白PET阳性分类模型在阿尔茨海默病连续谱中的研究
本研究利用阿尔茨海默病神经影像学倡议和韩国脑老化研究等数据,构建基于2-[18F]FDG PET图像的2.5维深度学习模型,用于分类淀粉样蛋白PET阳性。模型在内部验证集AUC为0.811(95%CI 0.803-0.819),外部验证集AUC为0.798(95%CI 0.789-0.807),最佳模型外部验证AUC达0.860,准确率75.0%、灵敏度76.0%、特异度74.0%、F1分数75.0%。结论提示该模型有望在无法进行淀粉样蛋白PET时辅助分类淀粉样蛋白阳性。
要点
- 基于2-[18F]FDG PET的深度学习模型可分类淀粉样蛋白PET阳性,外部验证最佳AUC为0.860。
- 模型在外部验证集准确率75.0%、灵敏度76.0%、特异度74.0%、F1分数75.0%。
- 分类高值区域与默认网络重叠,有助于理解模型分类依据。
核心结论
- 基于2-[18F]FDG PET影像数据和深度学习框架的模型可能在没有淀粉样蛋白PET的情况下成功分类淀粉样蛋白PET阳性。
研究设计与样本
- 使用阿尔茨海默病神经影像学倡议和韩国脑老化研究等2-[18F]FDG PET数据集开发模型,并采用另一家医院的独立数据集进行外部验证。
- 构建了使用291个子模块和三个轴图像作为输入的2.5维深度学习架构。
- 训练和内部验证数据集共1433例,其中686例(47.9%)为淀粉样蛋白PET阳性;外部验证数据集100例,其中50例(50%)为淀粉样蛋白PET阳性。
主要发现
- 经过50次模型训练和验证迭代,模型在内部验证集AUC为0.811(95%CI 0.803-0.819),外部验证集AUC为0.798(95%CI 0.789-0.807)。
- 在外部验证集上测试最高值(0.864)的模型时,AUC为0.860,准确率75.0%、灵敏度76.0%、特异度74.0%、F1分数75.0%。
- 基于体素的分析发现,淀粉样蛋白PET阳性和阴性参与者之间葡萄糖代谢存在显著差异的区域与默认网络重叠,并产生高分类值。
临床怎么用
- 该模型可能作为一种替代方法,在淀粉样蛋白PET可及性有限时辅助分类淀粉样蛋白PET阳性。
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
BACKGROUND: Considering the limited accessibility of amyloid position emission tomography (PET) in patients with dementia, we proposed a deep learning (DL)-based amyloid PET positivity classification model from PET images with 2-deoxy-2-[fluorine-18]fluoro-D-glucose (2-[18F]FDG). METHODS: We used 2-[18F]FDG PET datasets from the Alzheimer's Disease Neuroimaging Initiative and Korean Brain Aging Study for the Early diagnosis and prediction of Alzheimer's disease for model development. Moreover, we used an independent dataset from another hospital. A 2.5-D deep learning architecture was constructed using 291 submodules and three axes images as the input. We conducted the voxel-wise analysis to assess the regions with substantial differences in glucose metabolism between the amyloid PET-positive and PET-negative participants. This facilitated an understanding of the deep model classification. In addition, we compared these regions with the classification probability from the submodules. RESULTS: There were 686 out of 1433 (47.9%) and 50 out of 100 (50%) amyloid PET-positive participants in the training and internal validation datasets and the external validation datasets, respectively. With 50 times iterations of model training and validation, the model achieved an AUC of 0.811 (95% confidence interval (CI) of 0.803-0.819) and 0.798 (95% CI, 0.789-0.807) on the internal and external validation datasets, respectively. The area under the curve (AUC) was 0.860 when tested with the model with the highest value (0.864) on the external validation dataset. Moreover, it had 75.0% accuracy, 76.0% sensitivity, 74.0% specificity, and 75.0% F1-score. We found an overlap between the regions within the default mode network, thus generating high classification values. CONCLUSION: The proposed model based on the 2-[18F]FDG PET imaging data and a DL framework might successfully classify amyloid PET positivity in clinical practice, without performing amyloid PET, which have limited accessibility.
引用
- Kim S, Lee P, Oh KT, et al. Deep learning-based amyloid PET positivity classification model in the Alzheimer's disease continuum by using 2-[18F]FDG PET. EJNMMI Res. 2021. PMID: 34114091. doi:10.1186/s13550-021-00798-3
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。