Saved in:
Bibliographic Details
Main Authors: Zhang, Qing, Pei, Guoquan, Wang, Yan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.06606
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913933446610944
author Zhang, Qing
Pei, Guoquan
Wang, Yan
author_facet Zhang, Qing
Pei, Guoquan
Wang, Yan
contents Medical Hyperspectral Imaging (MHSI) has emerged as a promising tool for enhanced disease diagnosis, particularly in computational pathology, offering rich spectral information that aids in identifying subtle biochemical properties of tissues. Despite these advantages, effectively fusing both spatial-dimensional and spectral-dimensional information from MHSIs remains challenging due to its high dimensionality and spectral redundancy inherent characteristics. To solve the above challenges, we propose a novel spatial-spectral omni-fusion network for hyperspectral image segmentation, named as Omni-Fuse. Here, we introduce abundant cross-dimensional feature fusion operations, including a cross-dimensional enhancement module that refines both spatial and spectral features through bidirectional attention mechanisms, a spectral-guided spatial query selection to select the most spectral-related spatial feature as the query, and a two-stage cross-dimensional decoder which dynamically guide the model to focus on the selected spatial query. Despite of numerous attention blocks, Omni-Fuse remains efficient in execution. Experiments on two microscopic hyperspectral image datasets show that our approach can significantly improve the segmentation performance compared with the state-of-the-art methods, with over 5.73 percent improvement in DSC. Code available at: https://github.com/DeepMed-Lab-ECNU/Omni-Fuse.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06606
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Omni-Fusion of Spatial and Spectral for Hyperspectral Image Segmentation
Zhang, Qing
Pei, Guoquan
Wang, Yan
Computer Vision and Pattern Recognition
Medical Hyperspectral Imaging (MHSI) has emerged as a promising tool for enhanced disease diagnosis, particularly in computational pathology, offering rich spectral information that aids in identifying subtle biochemical properties of tissues. Despite these advantages, effectively fusing both spatial-dimensional and spectral-dimensional information from MHSIs remains challenging due to its high dimensionality and spectral redundancy inherent characteristics. To solve the above challenges, we propose a novel spatial-spectral omni-fusion network for hyperspectral image segmentation, named as Omni-Fuse. Here, we introduce abundant cross-dimensional feature fusion operations, including a cross-dimensional enhancement module that refines both spatial and spectral features through bidirectional attention mechanisms, a spectral-guided spatial query selection to select the most spectral-related spatial feature as the query, and a two-stage cross-dimensional decoder which dynamically guide the model to focus on the selected spatial query. Despite of numerous attention blocks, Omni-Fuse remains efficient in execution. Experiments on two microscopic hyperspectral image datasets show that our approach can significantly improve the segmentation performance compared with the state-of-the-art methods, with over 5.73 percent improvement in DSC. Code available at: https://github.com/DeepMed-Lab-ECNU/Omni-Fuse.
title Omni-Fusion of Spatial and Spectral for Hyperspectral Image Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.06606