Tractography-Guided Dual-Label Collaborative Learning for Multi-Modal Cranial Nerves Parcellation

TL;DR

This paper introduces a novel multi-modal cranial nerve parcellation network that leverages tractography-guided dual-label learning and a modality-adaptive encoder to improve segmentation accuracy using structural and diffusion MRI data.

Contribution

The work proposes a dual-label collaborative learning framework with tractography-guided coarse labels and a new encoder module, enhancing multi-modal CNs parcellation performance.

Findings

Improved segmentation accuracy over single-label methods.

Effective use of tractography-guided coarse labels.

Validation on HCP dataset confirms robustness.

Abstract

The parcellation of Cranial Nerves (CNs) serves as a crucial quantitative methodology for evaluating the morphological characteristics and anatomical pathways of specific CNs. Multi-modal CNs parcellation networks have achieved promising segmentation performance, which combine structural Magnetic Resonance Imaging (MRI) and diffusion MRI. However, insufficient exploration of diffusion MRI information has led to low performance of existing multi-modal fusion. In this work, we propose a tractography-guided Dual-label Collaborative Learning Network (DCLNet) for multi-modal CNs parcellation. The key contribution of our DCLNet is the introduction of coarse labels of CNs obtained from fiber tractography through CN atlas, and collaborative learning with precise labels annotated by experts. Meanwhile, we introduce a Modality-adaptive Encoder Module (MEM) to achieve soft information swapping between structural MRI and diffusion MRI. Extensive experiments conducted on the publicly available Human Connectome Project (HCP) dataset demonstrate performance improvements compared to single-label network. This systematic validation underscores the effectiveness of dual-label strategies in addressing inherent ambiguities in CNs parcellation tasks.