English

Integrative Variational Autoencoders for Generative Modeling of an Image Outcome with Multiple Input Images

Image and Video Processing 2025-09-15 v2 Computer Vision and Pattern Recognition Neural and Evolutionary Computing Applications Machine Learning

Abstract

Understanding relationships across multiple imaging modalities is central to neuroimaging research. We introduce the Integrative Variational Autoencoder (InVA), the first hierarchical VAE framework for image-on-image regression in multimodal neuroimaging. Unlike standard VAEs, which are not designed for predictive integration across modalities, InVA models outcome images as functions of both shared and modality-specific features. This flexible, data-driven approach avoids rigid assumptions of classical tensor regression and outperforms conventional VAEs and nonlinear models such as BART. As a key application, InVA accurately predicts costly PET scans from structural MRI, offering an efficient and powerful tool for multimodal neuroimaging.

Keywords

Cite

@article{arxiv.2402.02734,
  title  = {Integrative Variational Autoencoders for Generative Modeling of an Image Outcome with Multiple Input Images},
  author = {Bowen Lei and Yeseul Jeon and Rajarshi Guhaniyogi and Aaron Scheffler and Bani Mallick and Alzheimer's Disease Neuroimaging Initiatives},
  journal= {arXiv preprint arXiv:2402.02734},
  year   = {2025}
}