An Efficient Cross-Modal Interaction and Dynamic Fusion Network for Multimodal Breast Ultrasound Diagnosis
Tomography · 25.06.2026 · 12 (7) · 93
DOI: 10.3390/tomography12070093 ↗Kurz gefasst
Fachartikel in der Zeitschrift Tomography, online erschienen am 25.06.2026. Verfasst von Xiangqiong Wu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Hunan First Normal University, Changsha 410205, China. Hauptthemen laut MEDLINE: Ultrasonography, Mammary, Multimodal Imaging, Breast Neoplasms, Image Interpretation, Computer-Assisted. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hunan Province.
Abstract (Originalsprache)
Background
Multimodal breast ultrasound, including B-mode imaging, color Doppler flow imaging, and elastography, provides complementary information for lesion characterization. However, effectively integrating heterogeneous modalities remains challenging due to inconsistent feature distributions, limited cross-modal interaction, computational cost in existing methods, and sensitivity to noise and missing data.
Methods
We presented an efficient Cross-Modal Interaction and Dynamic Fusion Network (CIDFNet) for multimodal breast ultrasound analysis. The framework integrates a multi-scale feature enhancement module to improve modality-specific representations, a cross-modal interaction module to enable early-stage feature exchange across modalities, and a dynamic fusion strategy to adaptively combine modality information based on feature reliability estimation. In addition, an invertible neural network is incorporated to reconstruct missing modality features during training.
Results
Experiments on an internal dataset of 248 patients with 1532 images show that CIDFNet obtains an AUC of 85.69%, accuracy of 75.51%, recall of 50.00%, F1-score of 62.50%, and precision of 83.33%, while requiring 49.51 M parameters and 79.79 G FLOPs, respectively. Under a simplified Gaussian noise perturbation setting, performance degradation is observed.
Conclusions
CIDFNet presents a framework for multimodal breast ultrasound analysis that reflects a trade-off between performance and computational efficiency.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science, Hunan First Normal University, Changsha 410205, China.
- School of Electronic Information, Hunan First Normal University, Changsha 410205, China.
ORCID-Profile: Xiangqiong Wu, Yin Lan, Lina Han
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Hunan Province
Zitieren
APA
Wu, X., Lan, Y., Han, L., & Wang, P. (2026). An Efficient Cross-Modal Interaction and Dynamic Fusion Network for Multimodal Breast Ultrasound Diagnosis. Tomography, 12(7), 93. https://doi.org/10.3390/tomography12070093
Vancouver
Wu X, Lan Y, Han L, Wang P. An Efficient Cross-Modal Interaction and Dynamic Fusion Network for Multimodal Breast Ultrasound Diagnosis. Tomography. 2026;12(7):93. doi:10.3390/tomography12070093
BibTeX
@article{Wu2026,
author = {Wu, Xiangqiong and Lan, Yin and Han, Lina and Wang, Peng},
title = {An Efficient Cross-Modal Interaction and Dynamic Fusion Network for Multimodal Breast Ultrasound Diagnosis},
journal = {Tomography},
year = {2026},
volume = {12},
number = {7},
pages = {93},
doi = {10.3390/tomography12070093}
}
EUVIMED