基于深度学习FDG PET聚类识别阿尔茨海默病空间脑代谢模式的独特亚型
研究从ADNI数据库获取1607名参与者在入组和随访时的3620幅FDG脑PET图像(含AD、MCI和认知正常),训练条件变分自编码器模型并以kmeans聚类,识别出四种AD空间代谢模式亚型,并将模型迁移至MCI以预测其向AD转化的预后。
要点
- 识别出四种AD空间代谢模式亚型:角回型、枕叶型、眶额型和轻微低代谢型。
- 模型成功迁移用于MCI亚型分型,各亚型间转化频率(P < 0.001)和转化风险(logrank P < 0.0001)存在显著差异。
- MCI向AD转化率最高为S2(35.7%),其次为S1(23.4%)。
核心结论
- 研究识别出具有不同临床病理特征的AD独特亚型,基于深度学习在FDG PET上区分AD亚型可能有助于预测个体结局并为理解AD异质性病理生理提供线索。
研究设计与样本
- 从ADNI数据库获取1607名参与者在入组和随访时的3620幅FDG脑PET图像,涵盖AD、MCI和认知正常。
- 在AD患者FDG脑PET图像上以AD严重程度评分为条件训练条件变分自编码器模型,并用kmeans算法对编码表示进行聚类。
- 将训练好的深度学习聚类模型迁移至MCI患者的FDG PET,预测其向AD转化的亚型预后。
主要发现
- 识别出四种AD空间代谢模式亚型:角回型、枕叶型、眶额型和轻微低代谢型,具有不同脑病理和临床特征。
- 深度学习模型成功迁移用于MCI亚型分型,各亚型间MCI向AD的转化频率差异显著(P < 0.001),转化风险差异显著(logrank P < 0.0001)。
- MCI向AD转化率最高为S2(35.7%),其次为S1(23.4%)。
关键数值与推荐
- 四种AD亚型:角回型、枕叶型、眶额型、轻微低代谢型。
- MCI向AD转化频率在各亚型间P < 0.001,转化风险logrank P < 0.0001。
- MCI向AD转化率S2为35.7%,S1为23.4%。
临床怎么用
- 原文未据此给出临床推荐。
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
PURPOSE: Alzheimer's disease (AD) is a heterogeneous disease that presents a broad spectrum of clinicopathologic profiles. To date, objective subtyping of AD independent of disease progression using brain imaging has been required. Our study aimed to extract representations of unique brain metabolism patterns different from disease progression to identify objective subtypes of AD. METHODS: A total of 3620 FDG brain PET images with AD, mild cognitive impairment (MCI), and cognitively normal (CN) were obtained from the ADNI database from 1607 participants at enrollment and follow-up visits. A conditional variational autoencoder model was trained on FDG brain PET images of AD patients with the corresponding condition of AD severity score. The k-means algorithm was applied to generate clusters from the encoded representations. The trained deep learning-based cluster model was also transferred to FDG PET of MCI patients and predicted the prognosis of subtypes for conversion from MCI to AD. Spatial metabolism patterns, clinical and biological characteristics, and conversion rate from MCI to AD were compared across the subtypes. RESULTS: Four distinct subtypes of spatial metabolism patterns in AD with different brain pathologies and clinical profiles were identified: (i) angular, (ii) occipital, (iii) orbitofrontal, and (iv) minimal hypometabolic patterns. The deep learning model was also successfully transferred for subtyping MCI, and significant differences in frequency (P < 0.001) and risk of conversion (log-rank P < 0.0001) from MCI to AD were observed across the subtypes, highest in S2 (35.7%) followed by S1 (23.4%). CONCLUSION: We identified distinct subtypes of AD with different clinicopathologic features. The deep learning-based approach to distinguish AD subtypes on FDG PET could have implications for predicting individual outcomes and provide a clue to understanding the heterogeneous pathophysiology of AD.
引用
- Ryoo HG, Choi H, Shi K, et al. Distinct subtypes of spatial brain metabolism patterns in Alzheimer's disease identified by deep learning-based FDG PET clusters. Eur J Nucl Med Mol Imaging. 2023. PMID: 37735259. doi:10.1007/s00259-023-06440-9
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。