Integrative Variational Autoencoders for Generative Modeling of an Image Outcome with Multiple Input Images
This provides an efficient tool for predicting costly PET scans from structural MRI in neuroimaging research, though it appears incremental as it builds on existing VAE frameworks.
The authors tackled the problem of predicting one imaging modality from multiple others in neuroimaging by introducing the Integrative Variational Autoencoder (InVA), which outperformed conventional VAEs and nonlinear models like BART.
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.