Cross-domain Fiber Cluster Shape Analysis for Language Performance Cognitive Score Prediction

2024-03-27

arXiv.org

AI Summary

This study investigates the predictive value of three-dimensional (3D) white matter fiber shape features for individual language cognition. Method: We propose the Shape-fused Fiber Cluster Transformer (SFFormer), which reconstructs 3D fiber point sequences from diffusion MRI tractography, extracts 12-dimensional geometric shape descriptors, and—uniquely—integrates fiber cluster shape with multimodal features including microstructural properties and structural connectivity strength. A novel cross-domain multi-head cross-attention mechanism enables synergistic modeling across shape, microstructure, and connectivity domains. Contribution/Results: Evaluated on 1,065 healthy young adults, SFFormer significantly improves regression accuracy for language scores (p < 0.001), demonstrating that 3D fiber geometry provides independent and complementary predictive power for cognition. This work establishes a new geometric representation paradigm for connectomics.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Lexical Semantics and Morphology
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Shape plays an important role in computer graphics, offering informative features to convey an object's morphology and functionality. Shape analysis in brain imaging can help interpret structural and functionality correlations of the human brain. In this work, we investigate the shape of the brain's 3D white matter connections and its potential predictive relationship to human cognitive function. We reconstruct brain connections as sequences of 3D points using diffusion magnetic resonance imaging (dMRI) tractography. To describe each connection, we extract 12 shape descriptors in addition to traditional dMRI connectivity and tissue microstructure features. We introduce a novel framework, Shape--fused Fiber Cluster Transformer (SFFormer), that leverages a multi-head cross-attention feature fusion module to predict subject-specific language performance based on dMRI tractography. We assess the performance of the method on a large dataset including 1065 healthy young adults. The results demonstrate that both the transformer-based SFFormer model and its inter/intra feature fusion with shape, microstructure, and connectivity are informative, and together, they improve the prediction of subject-specific language performance scores. Overall, our results indicate that the shape of the brain's connections is predictive of human language function.

Problem

• Predict language performance using brain connection shapes
• Analyze 3D white matter shapes via dMRI tractography
• Fuse shape, microstructure, connectivity for cognitive prediction

Innovation

• Uses 3D white matter connection shape analysis
• Introduces Shape-fused Fiber Cluster Transformer (SFFormer)
• Combines shape, microstructure, and connectivity features