Multi-modal analysis of genetically-related subjects using SIFT descriptors in brain MRI

TL;DR

This paper introduces a multi-modal MRI analysis framework using SIFT features to compare genetically-related subjects, revealing strong links between MRI-based similarity and genetic proximity.

Contribution

It presents a novel multi-modal analysis method that employs SIFT features and graph-based similarity measures for comparing brain MRI data across different modalities.

Findings

Strong correlation between MRI-based similarity and genetic proximity.

Effective multi-modal comparison using SIFT features across T1/T2 and diffusion MRI.

Framework applicable to large datasets like the Human Connectome Project.

Abstract

So far, fingerprinting studies have focused on identifying features from single-modality MRI data, which capture individual characteristics in terms of brain structure, function, or white matter microstructure. However, due to the lack of a framework for comparing across multiple modalities, studies based on multi-modal data remain elusive. This paper presents a multi-modal analysis of genetically-related subjects to compare and contrast the information provided by various MRI modalities. The proposed framework represents MRI scans as bags of SIFT features, and uses these features in a nearest-neighbor graph to measure subject similarity. Experiments using the T1/T2-weighted MRI and diffusion MRI data of 861 Human Connectome Project subjects demonstrate strong links between the proposed similarity measure and genetic proximity.