An Arbitrary-Modal Fusion Network for Volumetric Cranial Nerves Tract Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Lei, Zhou, Huajun, Huang, Junxiong, Huang, Jiahao, Zeng, Qingrun, He, Jianzhong, Zhang, Jiawei, Fan, Baohua, Li, Mingchu, Xie, Guoqiang, Chen, Hao, Feng, Yuanjing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912361170862080
author Xie, Lei
Zhou, Huajun
Huang, Junxiong
Huang, Jiahao
Zeng, Qingrun
He, Jianzhong
Zhang, Jiawei
Fan, Baohua
Li, Mingchu
Xie, Guoqiang
Chen, Hao
Feng, Yuanjing
author_facet Xie, Lei
Zhou, Huajun
Huang, Junxiong
Huang, Jiahao
Zeng, Qingrun
He, Jianzhong
Zhang, Jiawei
Fan, Baohua
Li, Mingchu
Xie, Guoqiang
Chen, Hao
Feng, Yuanjing
contents The segmentation of cranial nerves (CNs) tract provides a valuable quantitative tool for the analysis of the morphology and trajectory of individual CNs. Multimodal CNs tract segmentation networks, e.g., CNTSeg, which combine structural Magnetic Resonance Imaging (MRI) and diffusion MRI, have achieved promising segmentation performance. However, it is laborious or even infeasible to collect complete multimodal data in clinical practice due to limitations in equipment, user privacy, and working conditions. In this work, we propose a novel arbitrary-modal fusion network for volumetric CNs tract segmentation, called CNTSeg-v2, which trains one model to handle different combinations of available modalities. Instead of directly combining all the modalities, we select T1-weighted (T1w) images as the primary modality due to its simplicity in data acquisition and contribution most to the results, which supervises the information selection of other auxiliary modalities. Our model encompasses an Arbitrary-Modal Collaboration Module (ACM) designed to effectively extract informative features from other auxiliary modalities, guided by the supervision of T1w images. Meanwhile, we construct a Deep Distance-guided Multi-stage (DDM) decoder to correct small errors and discontinuities through signed distance maps to improve segmentation accuracy. We evaluate our CNTSeg-v2 on the Human Connectome Project (HCP) dataset and the clinical Multi-shell Diffusion MRI (MDM) dataset. Extensive experimental results show that our CNTSeg-v2 achieves state-of-the-art segmentation performance, outperforming all competing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02385
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Arbitrary-Modal Fusion Network for Volumetric Cranial Nerves Tract Segmentation
Xie, Lei
Zhou, Huajun
Huang, Junxiong
Huang, Jiahao
Zeng, Qingrun
He, Jianzhong
Zhang, Jiawei
Fan, Baohua
Li, Mingchu
Xie, Guoqiang
Chen, Hao
Feng, Yuanjing
Image and Video Processing
Computer Vision and Pattern Recognition
The segmentation of cranial nerves (CNs) tract provides a valuable quantitative tool for the analysis of the morphology and trajectory of individual CNs. Multimodal CNs tract segmentation networks, e.g., CNTSeg, which combine structural Magnetic Resonance Imaging (MRI) and diffusion MRI, have achieved promising segmentation performance. However, it is laborious or even infeasible to collect complete multimodal data in clinical practice due to limitations in equipment, user privacy, and working conditions. In this work, we propose a novel arbitrary-modal fusion network for volumetric CNs tract segmentation, called CNTSeg-v2, which trains one model to handle different combinations of available modalities. Instead of directly combining all the modalities, we select T1-weighted (T1w) images as the primary modality due to its simplicity in data acquisition and contribution most to the results, which supervises the information selection of other auxiliary modalities. Our model encompasses an Arbitrary-Modal Collaboration Module (ACM) designed to effectively extract informative features from other auxiliary modalities, guided by the supervision of T1w images. Meanwhile, we construct a Deep Distance-guided Multi-stage (DDM) decoder to correct small errors and discontinuities through signed distance maps to improve segmentation accuracy. We evaluate our CNTSeg-v2 on the Human Connectome Project (HCP) dataset and the clinical Multi-shell Diffusion MRI (MDM) dataset. Extensive experimental results show that our CNTSeg-v2 achieves state-of-the-art segmentation performance, outperforming all competing methods.
title An Arbitrary-Modal Fusion Network for Volumetric Cranial Nerves Tract Segmentation
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.02385