Multimodal MRI dataset and network improve cranial nerve identification
CNsEMD: An Expert-Annotated Multi-Field-Strength MRI Dataset and a Hyperspherical Manifold Network for Multimodal Cranial Nerve Parcellation
Computer Vision and Pattern Recognition
Summary
Cranial nerves are tiny nerves in the head responsible for many important functions, but they are very hard to see clearly in MRI scans. The authors created a new, expert-labeled dataset that includes MRI images from different scanner strengths to help identify these nerves better. They also developed a special computer network that uses a unique way of combining different MRI data to improve nerve detection. Their approach shows better results than previous methods and creates a reliable tool for studying these important nerves across various MRI machines.
cranial nervesMRImultimodal imaginghyperspherical manifoldmachine learningimage segmentationdiffusion MRIT1-weighted MRIdeep learningneuroanatomy
Authors
Lei Xie, Junxiong Huang, Guoqiang Xie, Jiawei Zhang, Jiahao Huang, Tianling Lyu, Ye Wu, Mingchu Li, Shoujun Yu, Shanshan Wang, Qingrun Zeng, Yuanjing Feng
Abstract
Cranial nerves (CNs) play essential roles in sensory, motor, and autonomic functions. Accurate CN parcellation from multimodal magnetic resonance imaging (MRI) is crucial for neuroanatomical analysis and neurosurgical planning. However, accurate CN parcellation remains extremely challenging because CNs are very small, exhibit low image contrast, and have slender tubular morphologies and complex anatomical trajectories. Moreover, the lack of publicly available, expert-annotated datasets has impeded the development and fair benchmarking of learning-based CN analysis methods. In this work, we introduce CNsEMD, an expert-annotated multimodal dataset for CN parcellation. It comprises data from 202 subjects acquired on 3T, 5T, and 7T MRI scanners. We further propose the projective hyperspherical manifold network (PHM-Net), which learns cross-modal representations by capturing angular relationships in a shared hyperspherical embedding space. Rather than performing multimodal fusion in Euclidean space, the proposed Hyperspherical cross-modal interaction (HCI) module enables bidirectional feature exchange between T1-weighted (T1w) and direction-encoded color (DEC) representations on a unit hypersphere. The Magnitude-preserving projective hyperspherical orientation representation (PHOR) captures the axial nature of DEC orientations while preserving diffusion magnitude. The hyperspherical prototype segmentation head (HPSH) further extends angular similarity to voxel-wise classification using normalized voxel embeddings and learnable class prototypes. Extensive experimental results on the CNsEMD dataset demonstrate the effectiveness of our PHM-Net against state-of-the-art methods. CNsEMD establishes a reproducible benchmark for multimodal CN imaging, while PHM-Net provides a geometry-consistent solution for CN parcellation across diverse MRI acquisitions.