DeepJIVE:利用深度学习从多模态数据中学习联合与个体变异解释
DeepJIVE: Learning Joint and Individual Variation Explained from Multimodal Data Using Deep Learning
AI总结:
本文提出深度学习方法 DeepJIVE,通过三种可行损失实现 JIVE 的恒等与正交约束,可在高维非线性多模态数据中提取联合及个体变异,并在 ADNI 的 PET 与 MR 图像中发现具生物学意义的协变模式。
摘要:
传统的多模态数据整合方法可对每种单独数据类型内部的共享或独特结构进行全面评估,但存在若干局限,例如无法处理高维数据以及不能识别非线性结构。本文提出 DeepJIVE,这是一种用于执行联合与个体变异解释(Joint and Individual Variance Explained,JIVE)的深度学习方法。我们使用合成数据集以及真实世界的一维、二维和三维数据集进行了数学推导和实验验证。研究探索了在 DeepJIVE 中实现恒等约束和正交约束的不同策略,得到了三种可行的损失函数。我们发现 DeepJIVE 能够成功揭示多模态数据集的联合变异和个体变异。将 DeepJIVE 应用于阿尔茨海默病神经影像学倡议(Alzheimer's Disease Neuroimaging Initiative,ADNI)数据集时,还识别出淀粉样蛋白正电子发射断层扫描(PET)图像与磁共振(MR)图像之间具有生物学合理性的协变模式。总之,所提出的 DeepJIVE 可成为多模态数据分析的有用工具。
英文摘要:
Conventional multimodal data integration methods provide a comprehensive assessment of the shared or unique structure within each individual data type but suffer from several limitations such as the inability to handle high-dimensional data and identify nonlinear structures. In this paper, we introduce DeepJIVE, a deep-learning approach to performing Joint and Individual Variance Explained (JIVE). We perform mathematical derivation and experimental validations using both synthetic and real-world 1D, 2D, and 3D datasets. Different strategies of achieving the identity and orthogonality constraints for DeepJIVE were explored, resulting in three viable loss functions. We found that DeepJIVE can successfully uncover joint and individual variations of multimodal datasets. Our application of DeepJIVE to the Alzheimer's Disease Neuroimaging Initiative (ADNI) also identified biologically plausible covariation patterns between the amyloid positron emission tomography (PET) and magnetic resonance (MR) images. In conclusion, the proposed DeepJIVE can be a useful tool for multimodal data analysis.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。