Semantic Integration of Multi-Modal Data and Derived Neuroimaging Results Using the Platform for Imaging in Precision Medicine (PRISM) in the Arkansas Imaging Enterprise System (ARIES).

Jonathan Bona,Fred Prior,Aparna Das,Carli Cox,Lakshmi Pillai,Tuhin Virmani,Aaron S Kemp,Tracy S Nolan,James E Galvin,Linda Larson-Prior

doi:10.3389/frai.2021.649970

Abstract

Neuroimaging is among the most active research domains for the creation and management of open-access data repositories. Notably lacking from most data repositories are integrated capabilities for semantic representation. The Arkansas Imaging Enterprise System (ARIES) is a research data management system which features integrated capabilities to support semantic representations of multi-modal data from disparate sources (imaging, behavioral, or cognitive assessments), across common image-processing stages (preprocessing steps, segmentation schemes, analytic pipelines), as well as derived results (publishable findings). These unique capabilities ensure greater reproducibility of scientific findings across large-scale research projects. The current investigation was conducted with three collaborating teams who are using ARIES in a project focusing on neurodegeneration. Datasets included magnetic resonance imaging (MRI) data as well as non-imaging data obtained from a variety of assessments designed to measure neurocognitive functions (performance scores on neuropsychological tests). We integrate and manage these data with semantic representations based on axiomatically rich biomedical ontologies. These instantiate a knowledge graph that combines the data from the study cohorts into a shared semantic representation that explicitly accounts for relations among the entities that the data are about. This knowledge graph is stored in a triple-store database that supports reasoning over and querying these integrated data. Semantic integration of the non-imaging data using background information encoded in biomedical domain ontologies has served as a key feature-engineering step, allowing us to combine disparate data and apply analyses to explore associations, for instance, between hippocampal volumes and measures of cognitive functions derived from various assessment instruments.

Highlights

Neuroimaging is among the most active research domains for the creation and management of open-access data repositories (Eickhoff et al, 2016)
By integrating these instance data using ontologies that contain the relevant background information in both human- and machineinterpretable forms, we greatly enhance its potential for reuse, enable automated inference over these data using semantic web tools, and create a richly-labeled dataset amenable to use with other artificial intelligence approaches, including statistical and machine learning based uses of these data
The Arkansas Imaging Enterprise System (ARIES) leverages the basic capabilities of the Platform for Imaging in Precision Medicine (PRISM) to effectively represent and integrate a diverse set of multi-modal data elements and provide detailed descriptions of the results obtained across the analytic processing stages and in relation to the supporting endophenotypic data

Summary

Introduction

Neuroimaging is among the most active research domains for the creation and management of open-access data repositories (Eickhoff et al, 2016). Research investigations of brain disorders frequently employ neuroimaging in conjunction with established assessment instruments that have been venerated by years of clinical usage and/or validated as clinically meaningful measures of a given symptom, behavior, or functional domain of interest. Use of such condition-specific measures across studies poses unique challenges, when mining neuroimaging data repositories that were originally collected for specific brain disorders, such as the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (Mueller et al, 2005) or the Progressive Parkinson’s Markers Initiative (PPMI) (Marek et al, 2011). Integrating shared semantic representations across the neuroimaging data, derived imaging measures, and associated non-imaging assessment data is a critical step in seeking to apply reasoning and inferencing to detect either common or discriminative patterns of association across various brain disorders

Objectives

Methods

Results

Conclusion