Connectomics Informed by Large Language Models

2025-11-07

AI Summary

Conventional tractography algorithms struggle to simultaneously achieve high sensitivity and specificity in white-matter connectome mapping. Method: This paper introduces large language models (LLMs) to connectomics for the first time, proposing a neuroanatomy-informed framework for generating quantitative anatomical priors. Leveraging prompt engineering and integration of external anatomical knowledge, the LLM extracts structured, quantifiable pathway priors—including origin/termination regions, trajectory constraints, and probabilistic weights—and embeds them into tractography post-processing. Contribution/Results: The method significantly reduces both false-positive and false-negative connections, achieving state-of-the-art accuracy on the HCP-Diffusion gold-standard connectome atlas. It also enhances discriminative performance in downstream pathological diffusion modeling. Its core innovation lies in establishing the first LLM-driven, anatomy-aware connectomics pipeline that enables trustworthy translation of textual neuroanatomical knowledge into computationally usable priors.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Tractography is a unique method for mapping white matter connections in the brain, but tractography algorithms suffer from an inherent trade-off between sensitivity and specificity that limits accuracy. Incorporating prior knowledge of white matter anatomy is an effective strategy for improving accuracy and has been successful for reducing false positives and false negatives in bundle-mapping protocols. However, it is challenging to scale this approach for connectomics due to the difficulty in synthesising information relating to many thousands of possible connections. In this work, we develop and evaluate a pipeline using large language models (LLMs) to generate quantitative priors for connectomics, based on their knowledge of neuroanatomy. We benchmark our approach against an evaluation set derived from a gold-standard tractography atlas, identifying prompting techniques to elicit accurate connectivity information from the LLMs. We further identify strategies for incorporating external knowledge sources into the pipeline, which can provide grounding for the LLM and improve accuracy. Finally, we demonstrate how the LLM-derived priors can augment existing tractography filtering approaches by identifying true-positive connections to retain during the filtering process. We show that these additional connections can improve the accuracy of a connectome-based model of pathology spread, which provides supporting evidence that the connections preserved by the LLM are valid.

Problem

• Improving tractography accuracy by balancing sensitivity and specificity trade-offs
• Scaling neuroanatomy knowledge integration for comprehensive brain connectomics
• Generating quantitative priors using LLMs to enhance tractography filtering

Innovation

• Using LLMs to generate quantitative priors for connectomics
• Incorporating external knowledge sources to improve accuracy
• Augmenting tractography filtering by identifying true-positive connections