A dual-branch network for lesion segmentation in medical images using state space models
Quantitative Imaging in Medicine and Surgery · 2025-12 · 15 (12) · 11977-11991
DOI: 10.21037/qims-2025-576 ↗Kurz gefasst
Fachartikel in der Zeitschrift Quantitative Imaging in Medicine and Surgery, 2025-12. Verfasst von Hao Chen und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Nantong Institute of Technology, Nantong, China. Die Arbeit wurde bisher 5-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Lesion segmentation in medical images is crucial for clinical diagnosis and treatment planning. However, existing methods often struggle to effectively extract both local and global features, limiting segmentation accuracy. To address this challenge, we propose a dual-branch network that integrates state space models (SSMs) with deep convolutional networks to enhance the extraction of both local and global features, thus improving lesion segmentation performance.
Methods
The proposed model employs a dual-branch encoder: one branch incorporates the visual state space encoder to efficiently model long-range contextual dependencies, while the other branch, based on the residual network, extracts hierarchical local features. To refine feature representation, we introduce a lightweight multi-scale depth-wise separable convolution block, ensuring adaptability to varying lesion sizes while maintaining computational efficiency. The fused features are processed by the decoder for high-precision segmentation.
Results
Extensive experiments on the Kaggle_3M and Kvasir-SEG datasets demonstrated that the proposed model outperformed existing state-of-the-art models. Specifically, it achieved a dice similarity coefficient (Dice) of 0.9140 and a false negative rate (FNR) of 0.0800 on Kaggle_3M dataset, and a Dice of 0.9173 and an FNR of 0.0788 on Kvasir-SEG dataset. Compared to other models, our model delivered superior quantitative results and visual segmentation performance. In addition, when trained on Kvasir-SEG and tested on two external datasets, our model demonstrated superior cross-dataset generalization.
Conclusions
The proposed model integrates SSMs and deep convolutional networks to improve lesion segmentation by effectively capturing both local and global features. It offers new insights for medical image segmentation with potential clinical applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Engineering, Nantong Institute of Technology, Nantong, China.
- Division of Information and Communication Convergence Engineering, Mokwon University, Daejeon, Republic of Korea.
ORCID-Profile: Hao Chen
Zitieren
APA
Chen, H., Min, B. W., & Zhang, H. (2025). A dual-branch network for lesion segmentation in medical images using state space models. Quantitative Imaging in Medicine and Surgery, 15(12), 11977-11991. https://doi.org/10.21037/qims-2025-576
Vancouver
Chen H, Min BW, Zhang H. A dual-branch network for lesion segmentation in medical images using state space models. Quantitative Imaging in Medicine and Surgery. 2025;15(12):11977-11991. doi:10.21037/qims-2025-576
BibTeX
@article{Chen2025,
author = {Chen, Hao and Min, Byung-Won and Zhang, Haifei},
title = {A dual-branch network for lesion segmentation in medical images using state space models},
journal = {Quantitative Imaging in Medicine and Surgery},
year = {2025},
volume = {15},
number = {12},
pages = {11977--11991},
doi = {10.21037/qims-2025-576}
}
EUVIMED