Dynamic Frequency-Decoupled Refinement Network for Polyp Segmentation
Bioengineering · 11.03.2025 · 12 (3) · 277
DOI: 10.3390/bioengineering12030277 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering, online erschienen am 11.03.2025. Verfasst von Yao Tong und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210023, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Development Plan of Traditional Chinese Medicine (TCM) in Jiangsu Province, Jiangsu Province Engineering Research Center of TCM Intelligence Health Service, National Natural Science Foundation of China.
Abstract (Originalsprache)
Polyp segmentation is crucial for early colorectal cancer detection, but accurately delineating polyps is challenging due to their variations in size, shape, and texture and low contrast with surrounding tissues. Existing methods often rely solely on spatial-domain processing, which struggles to separate high-frequency features (edges, textures) from low-frequency ones (global structures), leading to suboptimal segmentation performance. We propose the Dynamic Frequency-Decoupled Refinement Network (DFDRNet), a novel segmentation framework that integrates frequency-domain and spatial-domain processing. DFDRNet introduces the Frequency Adaptive Decoupling (FAD) module, which dynamically separates high- and low-frequency components, and the Frequency Adaptive Refinement (FAR) module, which refines these components before fusing them with spatial features to enhance segmentation accuracy. Embedded within a U-shaped encoder–decoder framework, DFDRNet achieves state-of-the-art performance across three benchmark datasets, demonstrating superior robustness and efficiency. Our extensive evaluations and ablation studies confirm the effectiveness of DFDRNet in balancing segmentation accuracy with computational efficiency.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210023, China.
- Jiangsu Province Engineering Research Center of TCM Intelligence Health Service, Nanjing University of Chinese Medicine, Nanjing 210023, China.
- Vanke School of Public Health, Tsinghua University, Beijing 100084, China.
- College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China.
- School of Elderly Care Services and Management, Nanjing University of Chinese Medicine, Nanjing 210023, China.
Förderung
- Development Plan of Traditional Chinese Medicine (TCM) in Jiangsu Province
- Jiangsu Province Engineering Research Center of TCM Intelligence Health Service
- National Natural Science Foundation of China
- National Key Research and Development Program of China
- Nanjing University of Chinese Medicine Education and Teaching Research Project
- Jiangsu Province Social Science Applied Research Excellent Project Project
Zitieren
APA
Tong, Y., Chai, J., Chen, Z., Zhou, Z., Hu, Y., Li, X., Qiao, X., & Hu, K. (2025). Dynamic Frequency-Decoupled Refinement Network for Polyp Segmentation. Bioengineering, 12(3), 277. https://doi.org/10.3390/bioengineering12030277
Vancouver
Tong Y, Chai J, Chen Z, Zhou Z, Hu Y, Li X, et al. Dynamic Frequency-Decoupled Refinement Network for Polyp Segmentation. Bioengineering. 2025;12(3):277. doi:10.3390/bioengineering12030277
BibTeX
@article{Tong2025,
author = {Tong, Yao and Chai, Jingxian and Chen, Ziqi and Zhou, Zuojian and Hu, Yun and Li, Xin and Qiao, Xuebin and Hu, Kongfa},
title = {Dynamic Frequency-Decoupled Refinement Network for Polyp Segmentation},
journal = {Bioengineering},
year = {2025},
volume = {12},
number = {3},
pages = {277},
doi = {10.3390/bioengineering12030277}
}
EUVIMED