MRANet: Multi‐Dimensional Residual Attentional Network for Precise Polyp Segmentation
IET Systems Biology · 2025-01 · 19 (1)
DOI: 10.1049/syb2.70031 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Systems Biology, online erschienen am 17.08.2025. Verfasst von Li Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer and Information Techonology, Xinyang Normal University, Xinyang, China. Hauptthemen laut MEDLINE: Colonic Polyps, Image Processing, Computer-Assisted, Neural Networks, Computer. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Henan Provincial Science and Technology Program, Henan Joint Fund for Science and Technology Research, Key Scientific Research Projects of Higher Education Institutions in Henan Province.
Abstract (Originalsprache)
Automated polyp detection plays a critical role in the early diagnosis of colorectal cancer, ranking as the second leading cause of cancer‐related mortality worldwide. However, existing segmentation methods face difficulties in handling complex polyp shapes, size variations, and generalising across diverse datasets. We propose a Multi‐dimensional Residual Attention Network (MRANet) for the polyp segmentation task, focusing on enhancing feature representation and ensuring robust performance across diverse clinical scenarios. During encoding, MRANet employs residual self‐attention to capture semantic information of high‐level features, guiding the refinement of low‐level information. In addition, convolutions with Multiple Kernel and Dilation rates (CMKD) are integrated with residual channel and spatial attentions to expand the model's receptive field, enhance encoder features, and accelerate convergence. In the decoding stage, MRANet uses the proposed Attention‐based Scale Interaction Module (ASIM) to merge upsampled high‐level features with low‐level pixel information, enriching low‐level layers using semantic knowledge. A Residual‐based Scale Fusion Module (RSFM) is further designed to merge low‐level features, which preserves high‐frequency details including edges and textures. Experiments demonstrate that MRANet effectively segments polyps with varying sizes, indistinct boundaries, and scattered distributions, achieving the best overall performance. Our code is available at https://github.com/hpguo1982/MRANet .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer and Information Techonology, Xinyang Normal University, Xinyang, China.
- School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China.
- Information Center, Xinyang Agricultural and Forestry University, Xinyang, China.
ORCID-Profile: Li Zhang, Huaping Guo
Förderung
- Henan Provincial Science and Technology Program
- Henan Joint Fund for Science and Technology Research
- Key Scientific Research Projects of Higher Education Institutions in Henan Province
- Open Fund of the Engineering Research Center of Intelligent Swarm Systems, Ministry of Education
Zitieren
APA
Zhang, L., Zeng, Y., Sun, Y., Zheng, C., Feng, Y., & Guo, H. (2025). MRANet: Multi‐Dimensional Residual Attentional Network for Precise Polyp Segmentation. IET Systems Biology, 19(1). https://doi.org/10.1049/syb2.70031
Vancouver
Zhang L, Zeng Y, Sun Y, Zheng C, Feng Y, Guo H. MRANet: Multi‐Dimensional Residual Attentional Network for Precise Polyp Segmentation. IET Systems Biology. 2025;19(1). doi:10.1049/syb2.70031
BibTeX
@article{Zhang2025,
author = {Zhang, Li and Zeng, Yu and Sun, Yange and Zheng, Chengyi and Feng, Yan and Guo, Huaping},
title = {MRANet: Multi‐Dimensional Residual Attentional Network for Precise Polyp Segmentation},
journal = {IET Systems Biology},
year = {2025},
volume = {19},
number = {1},
doi = {10.1049/syb2.70031}
}
EUVIMED