3DWaFusion: Three-Dimensional Multiscale Wavelet Convolutional Neural Network for Multimodal Medical Image Fusion
Sensors · 2026
DOI: 10.3390/s26123784 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Yu Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and A…. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Wavelet Analysis, Multimodal Imaging. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Jiangsu Province of China, NUAA Fundamental Research Funds for the Central Universities, Nanjing University of Aeronautics and Astronautics.
Abstract (Originalsprache)
Multimodal image fusion is a promising technology designed to fuse information from different medical sensors, which offer structured insights for disease diagnosis and treatment. However, existing 2D-centric fusion methods fail to capture 3D spatial continuity, and conventional wavelet-based approaches lack adaptability to diverse lesion regions and suffer from background artifacts. To address this issue, we propose a 3D multiscale wavelet convolutional neural network for multimodal medical image fusion. Specifically, a 3D Discrete Wavelet Transformation (3D DWT) is introduced to decompose input volumes into multi-frequency bands, isolating anatomical structures and lesion details while reducing 3D spatial redundancy. We embed hierarchical multiple frequency band into a Global and Local Feature Calibration (GLFC) module to adaptively enhance single-modal features by fusing global contextual information and local details. Furthermore, a pyramid group-wise multiscale feature interaction is proposed for capturing complementary features across different spatial scales. Finally, a voxel-wise weighted averaging strategy reconstructs the fused image by adaptively assigning contributions to each modality at every spatial position, effectively eliminating artifacts and improving the visual fidelity of the result. Extensive experiments on the BraTS2020 and Hecktor datasets demonstrate that our proposed method outperforms state-of-the-art (SOTA) fusion methods in both subjective visual quality and objective metrics. Moreover, downstream segmentation validation confirms that fused images from our method significantly improve tumor segmentation accuracy. The source code and pre-trained models will be publicly available.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China.
- Jinling Clinical Medical College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China.
ORCID-Profile: Yu Wang, Rui Zhang, Zhiqiang Zhang, Ningzhong Liu
Förderung
- Natural Science Foundation of Jiangsu Province of China
- NUAA Fundamental Research Funds for the Central Universities
- Nanjing University of Aeronautics and Astronautics
- National Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis
Zitieren
APA
Wang, Y., Zhang, R., Zhang, Z., Liu, N., & Wang, X. (2026). 3DWaFusion: Three-Dimensional Multiscale Wavelet Convolutional Neural Network for Multimodal Medical Image Fusion. Sensors. https://doi.org/10.3390/s26123784
Vancouver
Wang Y, Zhang R, Zhang Z, Liu N, Wang X. 3DWaFusion: Three-Dimensional Multiscale Wavelet Convolutional Neural Network for Multimodal Medical Image Fusion. Sensors. 2026. doi:10.3390/s26123784
BibTeX
@article{Wang2026,
author = {Wang, Yu and Zhang, Rui and Zhang, Zhiqiang and Liu, Ningzhong and Wang, Xiulai},
title = {3DWaFusion: Three-Dimensional Multiscale Wavelet Convolutional Neural Network for Multimodal Medical Image Fusion},
journal = {Sensors},
year = {2026},
doi = {10.3390/s26123784}
}
EUVIMED