MNM : Multi-level Neuroimaging Meta-analysis with Hyperbolic Brain-Text Representations

TL;DR

This paper introduces a hyperbolic geometry-based framework for neuroimaging meta-analysis that effectively captures hierarchical brain structures and semantic relationships, improving analysis robustness and interpretability.

Contribution

It presents a novel hyperbolic embedding approach that jointly models neuroimaging data and literature, enabling multi-level analysis with hierarchical and semantic insights.

Findings

Outperforms baseline methods in accuracy and robustness

Effectively captures hierarchical brain structures

Provides interpretable multi-level neuroimaging analysis

Abstract

Various neuroimaging studies suffer from small sample size problem which often limit their reliability. Meta-analysis addresses this challenge by aggregating findings from different studies to identify consistent patterns of brain activity. However, traditional approaches based on keyword retrieval or linear mappings often overlook the rich hierarchical structure in the brain. In this work, we propose a novel framework that leverages hyperbolic geometry to bridge the gap between neuroscience literature and brain activation maps. By embedding text from research articles and corresponding brain images into a shared hyperbolic space via the Lorentz model, our method captures both semantic similarity and hierarchical organization inherent in neuroimaging data. In the hyperbolic space, our method performs multi-level neuroimaging meta-analysis (MNM) by 1) aligning brain and text embeddings for semantic correspondence, 2) guiding hierarchy between text and brain activations, and 3) preserving the hierarchical relationships within brain activation patterns. Experimental results demonstrate that our model outperforms baselines, offering a robust and interpretable paradigm of multi-level neuroimaging meta-analysis via hyperbolic brain-text representation.