Deep multiview learning to identify imaging-driven subtypes in mild cognitive impairment.
Deep multiview learning to identify imaging-driven subtypes in mild cognitive impairment.
复制标题
深度多视图学习识别轻度认知障碍中的成像驱动亚型。
DOI：
10.1186/s12859-022-04946-x
复制
发表时间：
2022-09-29
影响因子：
3
通讯作者：
Shen, Li
中科院分区：
文献类型：
--
作者：
Feng, Yixue;Kim, Mansu;Yao, Xiaohui;Liu, Kefei;Long, Qi;Shen, Li
在阿尔茨海默病（AD）研究中，多模态成像分析可以揭示多种成像模式的互补信息，并进一步加深我们对疾病的理解。一个应用是使用无监督聚类来发现疾病亚型。然而，现有的聚类方法往往是直接应用于输入功能，并可能遭受灾难的维数与高维多模态数据。本研究的目的是使用基于深度广义典型相关分析（DGCCA）的多视图学习框架来识别轻度认知障碍（MCI）参与者的多模态成像驱动亚型，以从3种神经成像模态中学习具有低维度的共享潜在表征。DGCCA使用神经网络将非线性变换应用于输入视图，并且能够学习具有低维度的相关嵌入，这些嵌入比其线性对应物广义CCA（GCCA）捕获更多的方差。我们设计了实验来比较DGCCA嵌入与单模态特征和GCCA嵌入，通过使用无监督聚类从每个特征集中生成2个子类型。在我们的验证研究中，我们发现淀粉样蛋白PET成像与结构MRI和FDG PET相比具有最具鉴别力的特征，DGCCA从这些特征中学习，但GCCA没有。DGCCA亚型在5项认知评估、6项脑容量测量和向AD模式的转换中显示出差异性测量。此外，DGCCA MCI亚型证实了现有晚期MCI组未识别的具有强信号的AD遗传标记。总体而言，DGCCA能够通过学习非线性投影从多模态数据中学习有效的低维嵌入。从DGCCA嵌入生成的MCI亚型不同于现有的早期和晚期MCI组，并且与淀粉样蛋白PET特征鉴定的MCI亚型显示出最大的相似性。在我们的验证研究中，DGCCA亚型在认知测量、脑容量方面显示出不同的模式，并且能够识别AD遗传标记。这些发现表明了成像驱动亚型的前景及其在揭示早期和晚期MCI以外的疾病结构方面的能力。在线版本包含补充材料，可通过10.1186/s12859-022-04946-x获得。
In Alzheimer’s Diseases (AD) research, multimodal imaging analysis can unveil complementary information from multiple imaging modalities and further our understanding of the disease. One application is to discover disease subtypes using unsupervised clustering. However, existing clustering methods are often applied to input features directly, and could suffer from the curse of dimensionality with high-dimensional multimodal data. The purpose of our study is to identify multimodal imaging-driven subtypes in Mild Cognitive Impairment (MCI) participants using a multiview learning framework based on Deep Generalized Canonical Correlation Analysis (DGCCA), to learn shared latent representation with low dimensions from 3 neuroimaging modalities. DGCCA applies non-linear transformation to input views using neural networks and is able to learn correlated embeddings with low dimensions that capture more variance than its linear counterpart, generalized CCA (GCCA). We designed experiments to compare DGCCA embeddings with single modality features and GCCA embeddings by generating 2 subtypes from each feature set using unsupervised clustering. In our validation studies, we found that amyloid PET imaging has the most discriminative features compared with structural MRI and FDG PET which DGCCA learns from but not GCCA. DGCCA subtypes show differential measures in 5 cognitive assessments, 6 brain volume measures, and conversion to AD patterns. In addition, DGCCA MCI subtypes confirmed AD genetic markers with strong signals that existing late MCI group did not identify. Overall, DGCCA is able to learn effective low dimensional embeddings from multimodal data by learning non-linear projections. MCI subtypes generated from DGCCA embeddings are different from existing early and late MCI groups and show most similarity with those identified by amyloid PET features. In our validation studies, DGCCA subtypes show distinct patterns in cognitive measures, brain volumes, and are able to identify AD genetic markers. These findings indicate the promise of the imaging-driven subtypes and their power in revealing disease structures beyond early and late stage MCI. The online version contains supplementary material available at 10.1186/s12859-022-04946-x.
登录
查看更多内容
DOI：
10.1016/j.jalz.2015.05.001
发表时间：
2015-07
期刊：
Alzheimer's & dementia : the journal of the Alzheimer's Association
影响因子：
--
作者：
Jagust WJ;Landau SM;Koeppe RA;Reiman EM;Chen K;Mathis CA;Price JC;Foster NL;Wang AY
通讯作者：
Wang AY
影响因子：
14.9
作者：
Buniello, Annalisa;MacArthur, Jacqueline A. L.;Parkinson, Helen
通讯作者：
Parkinson, Helen
影响因子：
4.6
作者：
Mitelpunkt, Alexis;Galili, Tal;Benjamini, Yoav
通讯作者：
Benjamini, Yoav
DOI：
10.1016/j.jalz.2010.03.003
发表时间：
2010-05
期刊：
Alzheimer's & dementia : the journal of the Alzheimer's Association
影响因子：
--
作者：
Jagust WJ;Bandy D;Chen K;Foster NL;Landau SM;Mathis CA;Price JC;Reiman EM;Skovronsky D;Koeppe RA;Alzheimer's Disease Neuroimaging Initiative
通讯作者：
Alzheimer's Disease Neuroimaging Initiative
影响因子：
4.8
作者：
Jeon, Seun;Kang, Jae Myeong;Noh, Young
通讯作者：
Noh, Young