GenTract: Generative Global Tractography

2025-11-17

AI Summary

In white matter fiber tractography, local methods suffer from error accumulation and high false-positive rates, while global methods—though more anatomically consistent—exhibit prohibitive computational costs. This paper introduces the first generative global tractography framework, departing from conventional stepwise integration to directly synthesize anatomically plausible, complete fiber pathways end-to-end from diffusion MRI. It is the first to integrate diffusion models and flow matching into tractography, coupled with a joint global optimization strategy that simultaneously enforces anatomical plausibility and data fidelity. Evaluated on research-grade datasets, our method achieves 2.1× higher accuracy than the state-of-the-art TractOracle. Under low-resolution or high-noise conditions, it outperforms comparable approaches by an order of magnitude, markedly enhancing robustness and clinical applicability of fiber tractography.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation
• Security and Privacy: Data transparency and provenance

Abstract

Tractography is the process of inferring the trajectories of white-matter pathways in the brain from diffusion magnetic resonance imaging (dMRI). Local tractography methods, which construct streamlines by following local fiber orientation estimates stepwise through an image, are prone to error accumulation and high false positive rates, particularly on noisy or low-resolution data. In contrast, global methods, which attempt to optimize a collection of streamlines to maximize compatibility with underlying fiber orientation estimates, are computationally expensive. To address these challenges, we introduce GenTract, the first generative model for global tractography. We frame tractography as a generative task, learning a direct mapping from dMRI to complete, anatomically plausible streamlines. We compare both diffusion-based and flow matching paradigms and evaluate GenTract's performance against state-of-the-art baselines. Notably, GenTract achieves precision 2.1x higher than the next-best method, TractOracle. This advantage becomes even more pronounced in challenging low-resolution and noisy settings, where it outperforms the closest competitor by an order of magnitude. By producing tractograms with high precision on research-grade data while also maintaining reliability on imperfect, lower-resolution data, GenTract represents a promising solution for global tractography.

Problem

• Improving white-matter pathway reconstruction from diffusion MRI
• Reducing error accumulation and false positive rates in tractography
• Addressing computational expense of global tractography methods

Innovation

• Generative model for global tractography
• Direct mapping from dMRI to streamlines
• Flow matching and diffusion paradigms compared