Related Experiment Video
Updated: Jun 6, 2025
09:06
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
Published on: June 9, 2018
12.1K
Multimodal predictive modeling: Scalable imaging informed approaches to predict future brain health
Meenu Ajith1, Jeffrey S Spence2, Sandra B Chapman2
1Tri-Institutional Center for Translational Research in Neuroimaging and Data Science(TReNDS), Georgia State University, Georgia Institute of Technology, and Emory University, 55 Park Pl NE, Atlanta, 30303, GA, USA.
Journal of Neuroscience Methods
|November 28, 2024
Summary
Predicting future brain health is enhanced by integrating neuroimaging data. An image-assisted approach using a partially conditional variational autoencoder (PCVAE) improves prediction accuracy for future brain health constructs.
Area of Science:
- Neuroscience
- Computational Psychiatry
- Medical Imaging Analysis
Background:
- Predicting future brain health necessitates integrating diverse data sources.
- Neural patterns from neuroimaging are early indicators of future behavioral states.
Purpose of the Study:
- To introduce a multimodal predictive modeling approach for future behavioral outcomes.
- To evaluate an imaging-informed methodology against traditional methods.
Main Methods:
- Compared three approaches: assessment-only (SVR), neuroimaging-only (RF), and image-assisted.
- The image-assisted method integrated static functional network connectivity (sFNC) from rs-fMRI with assessments.
- Utilized a partially conditional variational autoencoder (PCVAE) for prediction.
Main Results:
- The image-assisted method demonstrated superior performance in predicting future brain health constructs and longitudinal changes.
- The PCVAE model effectively utilized neuroimaging data during training to enhance prediction accuracy from assessment data alone.
Conclusions:
- Neuroimaging-informed predictive modeling holds significant potential for understanding cognitive performance and neural connectivity.
- This approach advances the comprehension of complex relationships between brain structure, function, and behavior.
