Conference Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 88 - Recent Advances in Multimodal Neuroimaging Data Integration
Type: Invited
Date/Time: Monday, August 8, 2022 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistics in Imaging
Abstract #320393
Title: Supervised and Unsupervised Learning for Multimodal Data Integration
Author(s): Brian Caffo*
Companies: Johns Hopkins University
Keywords: multimodal; imaging; fmri; mri; neuroscience; machine learning

In this talk we consider variations on supervised and unsupervised learning techniques for integrating multiple data modalities in a single analysis. We first examine extensions of regression and principal components and then extend the methods to neural networks. We propose embedding structured linear and non-linear transformations of the high dimensional data within traditional approaches as a key component of achieving explainable multi-modal models. We apply the developed methods to experiments in computational biology including neuroimaging and genomic measurements.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2022 program