发表机构
Advanced Interdisciplinary Science and Technology, Zhejiang University of Technology; College of Information Engineering, Zhejiang University of Technology; School of Computer Science and Technology, Nanjing University of Science and Technology; Capital Medical University Xuanwu Hospital; Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Nuclear Industry 215 Hospital of Shaanxi Province（浙江工业大学先进跨学科科学与技术学院; 浙江工业大学信息工程学院; 南京理工大学计算机科学与技术学院; 首都医科大学宣武医院; 中国科学院深圳先进技术研究院保罗·C·劳特伯生物医学成像研究中心; 陕西省核工业二一五医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对脑神经分割因体积小、对比度低而困难且缺乏公开数据集的问题，本文提出专家标注的多场强MRI数据集CNsEMD及超球面流形网络PHM-Net，通过跨模态交互实现精确分割，实验验证其有效性。
AI 中文摘要
脑神经（CNs）在感觉、运动和自主神经功能中发挥重要作用。基于多模态磁共振成像（MRI）的精确脑神经分割对于神经解剖分析和神经外科手术规划至关重要。然而，由于脑神经体积非常小、图像对比度低、呈细长管状形态且解剖轨迹复杂，精确的脑神经分割仍然极具挑战性。此外，缺乏公开的、专家标注的数据集阻碍了基于学习的脑神经分析方法的发展和公平基准测试。在这项工作中，我们引入了CNsEMD，一个用于脑神经分割的专家标注多模态数据集。该数据集包含来自202名受试者的数据，这些数据是在3T、5T和7T MRI扫描仪上采集的。我们进一步提出了投影超球面流形网络（PHM-Net），该网络通过在共享的超球面嵌入空间中捕捉角度关系来学习跨模态表示。所提出的超球面跨模态交互（HCI）模块不是在欧几里得空间中进行多模态融合，而是在单位超球面上实现T1加权（T1w）和方向编码颜色（DEC）表示之间的双向特征交换。幅度保持的投影超球面方向表示（PHOR）在保留扩散幅度的同时捕捉DEC方向的轴向特性。超球面原型分割头（HPSH）进一步将角度相似性扩展到体素级分类，使用归一化体素嵌入和可学习的类原型。在CNsEMD数据集上进行的大量实验结果表明，我们的PHM-Net相对于最先进的方法具有有效性。CNsEMD为多模态脑神经成像建立了一个可复现的基准，而PHM-Net为不同MRI采集条件下的脑神经分割提供了一种几何一致的解决方案。
英文摘要
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.
