MSMFusion: A Method for Multiscale Dual-Path State Space Modeling for Multimodal Medical Image Fusion
Biosensors · 2026
DOI: 10.3390/bios16100576 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biosensors, 2026. Verfasst von Liping Yang und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Changchun University, No. 6543, Satellite Road, Changchun 130022, China. Hauptthemen laut MEDLINE: Multimodal Imaging, Image Processing, Computer-Assisted. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Changchun Tianqin Environmental Engineering Co., Ltd, Changchun Tianqin Environmental Engineering Co., Ltd..
Abstract (Originalsprache)
Multimodal medical image fusion aims to integrate information from different imaging techniques to generate a single fused image that is comprehensive and rich in detail. Structural and functional imaging provide high-resolution anatomical details and tissue metabolic information, respectively. Complementary fusion improves quantitative fusion quality and preserves structural and functional information in one view, which aids clinical interpretation. Currently, convolutional neural network-based methods struggle to efficiently capture global features, whereas Transformer-based models excel at global modeling but incur relatively high computational costs. To address the above issues, we propose MSMFusion, a multiscale state-space modeling method for complementary structural–functional medical image fusion. A multiscale feature extraction module first extracts modality-specific multiscale structural features; subsequently, a dual-path MSMamba establishes long-range dependencies with linear complexity: the full-resolution scanning path preserves fine boundaries and textures, while the downsampled scanning path models global context with a more compact sequence; finally, a gated adaptive fusion module estimates spatial–channel weights based on local content to selectively integrate anatomical structure and functional metabolic information. On the Harvard medical image dataset, MSMFusion achieves a mutual information of 2.2181, a peak signal-to-noise ratio of 32.9390, and a structural similarity of 0.7616 on the MRI–PET task, and also outperforms various representative methods based on CNN, GAN, Transformer, and Mamba on the MRI–CT and MRI–SPECT tasks. Compared with the Transformer backbone, MSMamba reduces the number of parameters from 7.201M to 4.154M and the FLOPs from 476.738G to 159.239G, achieving superior fusion quality at lower computational cost while simultaneously preserving fine anatomical structures and key functional information.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Computer Science and Technology, Changchun University, No. 6543, Satellite Road, Changchun 130022, China.
- Bethune First Clinical Medical College, Jilin University, Changchun 130021, China.
ORCID-Profile: Shu Li
Förderung
- Changchun Tianqin Environmental Engineering Co., Ltd
- Changchun Tianqin Environmental Engineering Co., Ltd.
Zitieren
APA
Yang, L., Sun, N., Sun, T., Chen, Y., Xiao, Y., Li, S., Jia, W., Luo, S., & Wang, W. (2026). MSMFusion: A Method for Multiscale Dual-Path State Space Modeling for Multimodal Medical Image Fusion. Biosensors. https://doi.org/10.3390/bios16100576
Vancouver
Yang L, Sun N, Sun T, Chen Y, Xiao Y, Li S, et al. MSMFusion: A Method for Multiscale Dual-Path State Space Modeling for Multimodal Medical Image Fusion. Biosensors. 2026. doi:10.3390/bios16100576
BibTeX
@article{Yang2026,
author = {Yang, Liping and Sun, Nairui and Sun, Tengchao and Chen, Yiming and Xiao, Yao and Li, Shu and Jia, Wei and Luo, Shaoshuai and Wang, Wei},
title = {MSMFusion: A Method for Multiscale Dual-Path State Space Modeling for Multimodal Medical Image Fusion},
journal = {Biosensors},
year = {2026},
doi = {10.3390/bios16100576}
}
EUVIMED