Xie Lei, Huang Jiahao, Yu Jiangli, Zeng Qingrun, Hu Qiming, Chen Zan, Xie Guoqiang, Feng Yuanjing
Institute of Information Processing and Automation, College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China.
Institute of Information Processing and Automation, College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China.
Med Image Anal. 2023 May;86:102766. doi: 10.1016/j.media.2023.102766. Epub 2023 Feb 10.
The segmentation of cranial nerves (CNs) tracts based on diffusion magnetic resonance imaging (dMRI) provides a valuable quantitative tool for the analysis of the morphology and course of individual CNs. Tractography-based approaches can describe and analyze the anatomical area of CNs by selecting the reference streamlines in combination with ROIs-based (regions-of-interests) or clustering-based. However, due to the slender structure of CNs and the complex anatomical environment, single-modality data based on dMRI cannot provide a complete and accurate description, resulting in low accuracy or even failure of current algorithms in performing individualized CNs segmentation. In this work, we propose a novel multimodal deep-learning-based multi-class network for automated cranial nerves tract segmentation without using tractography, ROI placement or clustering, called CNTSeg. Specifically, we introduced T1w images, fractional anisotropy (FA) images, and fiber orientation distribution function (fODF) peaks into the training data set, and design the back-end fusion module which uses the complementary information of the interphase feature fusion to improve the segmentation performance. CNTSeg has achieved the segmentation of 5 pairs of CNs (i.e. optic nerve CN II, oculomotor nerve CN III, trigeminal nerve CN V, and facial-vestibulocochlear nerve CN VII/VIII). Extensive comparisons and ablation experiments show promising results and are anatomically convincing even for difficult tracts. The code will be openly available at https://github.com/IPIS-XieLei/CNTSeg.
基于扩散磁共振成像（dMRI）的颅神经（CNs）束分割为分析单个颅神经的形态和走行提供了一种有价值的定量工具。基于纤维束成像的方法可以通过结合基于感兴趣区域（ROIs）或基于聚类的参考流线来描述和分析颅神经的解剖区域。然而，由于颅神经结构纤细且解剖环境复杂，基于dMRI的单模态数据无法提供完整准确的描述，导致当前算法在进行个体化颅神经分割时准确率较低甚至失败。在这项工作中，我们提出了一种新颖的基于多模态深度学习的多类网络，用于自动进行颅神经束分割，无需使用纤维束成像、ROI放置或聚类，称为CNTSeg。具体而言，我们将T1加权图像、分数各向异性（FA）图像和纤维取向分布函数（fODF）峰值引入训练数据集，并设计了后端融合模块，利用相间特征融合的互补信息来提高分割性能。CNTSeg已实现了5对颅神经（即视神经CN II、动眼神经CN III、三叉神经CN V和面-前庭蜗神经CN VII/VIII）的分割。广泛的比较和消融实验显示出了有前景的结果，并且即使对于困难的神经束在解剖学上也具有说服力。代码将在https://github.com/IPIS-XieLei/CNTSeg上公开提供。
