Department of Nuclear Medicine, Seoul National University Bundang Hospital, Seongnam, Republic of Korea.
Department of Nuclear Medicine, Seoul National University Hospital, 101, Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea.
Eur J Nucl Med Mol Imaging. 2024 Jan;51(2):443-454. doi: 10.1007/s00259-023-06440-9. Epub 2023 Sep 22.
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.
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.
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%).
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.
阿尔茨海默病（AD）是一种异质性疾病，表现出广泛的临床病理谱。迄今为止，使用脑成像对 AD 进行独立于疾病进展的客观亚型分类一直是必要的。我们的研究旨在提取与疾病进展不同的独特脑代谢模式的表示，以确定 AD 的客观亚型。
从 ADNI 数据库中获得了来自 1607 名参与者在入组和随访时的 3620 个 FDG 脑 PET 图像，这些图像包括 AD、轻度认知障碍（MCI）和认知正常（CN）。在 AD 患者的 FDG 脑 PET 图像上训练条件变分自动编码器模型，并根据 AD 严重程度评分的相应条件进行训练。应用 k-means 算法从编码表示中生成聚类。该基于深度学习的聚类模型也被转移到 MCI 患者的 FDG PET 中，并预测了从 MCI 到 AD 的亚型转化的预后。比较了不同亚型的空间代谢模式、临床和生物学特征以及从 MCI 到 AD 的转化率。
在 AD 中发现了 4 种具有不同脑病理学和临床特征的空间代谢模式的不同亚型：（i）角型，（ii）枕叶型，（iii）眶额型和（iv）最小代谢低下型。深度学习模型也成功地用于 MCI 的亚型分类，在从 MCI 到 AD 的频率（P < 0.001）和转化率（对数秩 P < 0.0001）方面观察到了显著差异，其中 S2 型（35.7%）最高，其次是 S1 型（23.4%）。
我们确定了具有不同临床病理特征的 AD 不同亚型。基于深度学习的方法在 FDG PET 上区分 AD 亚型可能对预测个体预后有意义，并为理解 AD 的异质病理生理学提供线索。
