A Novel Dual-Stream Framework for dMRI Tractography Streamline Classification with Joint dMRI and fMRI Data

2025-11-24

AI Summary

Existing white matter tract classification methods rely solely on streamline geometric features, limiting their ability to distinguish functionally distinct tracts with similar anatomical trajectories. To address this, we propose the first dual-stream deep learning framework integrating diffusion MRI (dMRI) and functional MRI (fMRI): one stream extracts full-trajectory structural features from dMRI streamlines, while the other models fMRI-derived functional signals at tract endpoints, enabling joint structural–functional representation. By jointly optimizing a pretrained backbone network and an endpoint functional signal auxiliary module, our method significantly improves streamline functional consistency. In cortical spinal tract parcellation into four somatotopic subregions, it achieves a 9.2% average accuracy gain over state-of-the-art methods. Ablation studies confirm the critical contributions of both the dual-stream architecture and functional signal modeling. This work establishes a novel paradigm for fine-grained white matter tract typing under multimodal functional constraints.

Technology Category

• Data Mining & Knowledge Management: Data Stream Mining
• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Web Mining and Content Analysis: Content-based information diffusion
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Streamline classification is essential to identify anatomically meaningful white matter tracts from diffusion MRI (dMRI) tractography. However, current streamline classification methods rely primarily on the geometric features of the streamline trajectory, failing to distinguish between functionally distinct fiber tracts with similar pathways. To address this, we introduce a novel dual-stream streamline classification framework that jointly analyzes dMRI and functional MRI (fMRI) data to enhance the functional coherence of tract parcellation. We design a novel network that performs streamline classification using a pretrained backbone model for full streamline trajectories, while augmenting with an auxiliary network that processes fMRI signals from fiber endpoint regions. We demonstrate our method by parcellating the corticospinal tract (CST) into its four somatotopic subdivisions. Experimental results from ablation studies and comparisons with state-of-the-art methods demonstrate our approach's superior performance.

Problem

• Classifying white matter tracts using joint dMRI and fMRI data
• Distinguishing functionally distinct fiber tracts with similar pathways
• Enhancing functional coherence in tract parcellation through dual-stream analysis

Innovation

• Dual-stream framework combines dMRI and fMRI data
• Pretrained backbone processes full streamline trajectories
• Auxiliary network analyzes fMRI signals from endpoints