RF1AG073297

Multi-Site Neuroimage Harmonization for Personalized Brain Disorder Analysis

Abstract

Predicting the future progression of preclinical Alzheimer's disease (AD), such as subjective cognitive decline (SCD), is essential for drug development and timely intervention to prevent further cognitive decline. Multi-site multimodal neuroimaging data, while increasingly employed to augment sample size and improve statistical power for investigating SCD and AD-related disorders (ADRD), are susceptible to inter-site and inter-modality data heterogeneity caused by differences in scanners/protocols, studied populations, and imaging modalities. Mitigating inter-site data heterogeneity, principled fusion of multimodal data, and precise interpretation of neuroimaging data can reduce bias in subsequent analyses and help avoid erroneous conclusions.

In this project, we will develop a set of computational tools, powered by advanced machine learning techniques, for multi-site data harmonization, multimodal data fusion, and personalized/subject-specific neuroimage interpretation for SCD progression prediction. These tools will be evaluated extensively on 5,300+ subjects with multimodal data (e.g., magnetic resonance imaging, positron emission tomography, and cerebrospinal fluid) involving 79 imaging centers. We propose three aims.

Aim 1: Development of both feature-level and image-level deep learning frameworks for multi-site data harmonization. Many studies ignore inter-site data heterogeneity by simply assuming a common data source. Our methods will allow feature-level harmonization for precision medicine and image-level harmonization targeting a broader range of applications. The developed models will be easy to train via unsupervised learning.

Aim 2: Development of a framework to effectively fuse multimodal data for subsequent analyses without discarding subjects who lack certain modalities. Existing studies usually require modality-complete subjects, limiting their utility in multi-site studies where many subjects may lack one or several modalities due to patient dropouts or failed scans. Our models can be trained with modality-missing subjects, and thus are practical with considerably better adaptability.

Aim 3: Development of a framework for fast and accurate neuroimage search to facilitate personalized analysis of SCD and ADRD. Interpreting neuroimaging data at the subject level is often challenging due to the ever-increasing amount of imaging information. Our method will help overcome this difficulty by scalable neuroimage search for subject-specific progression prediction of SCD and ADRD.

University Of North Carolina At Chapel Hill

93.866 - Aging Research

National Institute on Aging (NIA) [HHS - NIH]

Chapel Hill, North Carolina 275991350 United States

Single Zip Code

NIH Research Project Grant (Parent R01 Clinical Trial Not Allowed) (PA-20-185)