Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Sep 9.
doi: 10.1007/s11517-025-03440-9. Online ahead of print.

GESur_Net: attention-guided network for surgical instrument segmentation in gastrointestinal endoscopy

Yaru Ma  1 , Yuying Liu  1 , Xin Chen  2 , Zhongqing Zheng  2 , Yufeng Wang  3 , Siyang Zuo  4
Affiliations

GESur_Net: attention-guided network for surgical instrument segmentation in gastrointestinal endoscopy

Yaru Ma et al. Med Biol Eng Comput. .

Abstract

Surgical instrument segmentation plays an important role in robotic autonomous surgical navigation systems as it can accurately locate surgical instruments and estimate their posture, which helps surgeons understand the position and orientation of the instruments. However, there are still some problems affecting segmentation accuracy, like insufficient attention to the edges and center of surgical instruments, insufficient usage of low-level feature details, etc. To address these issues, a lightweight network for surgical instrument segmentation in gastrointestinal (GI) endoscopy (GESur_Net) is proposed. The pixel data aggregation (PDA) mechanism is proposed to analyze the pixel value distribution in the feature map to obtain the importance of each feature channel. The skip connection attention (SK_A) block is proposed to enhance the attention on critical regions of the surgical instruments. The global guidance attention (GGA) block is proposed to fuse high-level semantic information with low-level detailed features, enabling the acquisition of both fine-grained resolution and global semantic information. In addition, we constructed a new dataset, the Gastrointestinal Endoscopic Instrument (GEI) dataset, hoping to provide valuable resources for future research. Extensive experiments conducted on our presented GEI dataset and the Kvasir-instrument dataset demonstrate that the proposed GESur_Net increases the segmentation accuracy and outperforms state-of-the-art segmentation models.

Keywords: Attention mechanism; Deep learning; Endoscopic instrument; Gastrointestinal endoscopy; Semantic segmentation.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethical approval: Ethical approval. Approval was obtained from the ethics committee of Tianjin Medical University General Hospital (Ethics approval number: IRB2022-YX-046-01). Conflict of interest: The authors declare no competing interests.

References

    1. Liang T, Zhang C, Wang Y et al (2024) A novel miniature flexible robotic system for endoscopic mucosal dissection: an animal experimental study. J Robot Surg 18(1):17. https://doi.org/10.1007/s11701-023-01793-7 - DOI - PubMed
    1. Zhang C, Wang Y, Liang T, Kong K, Yao Q, Zuo S (2024) A novel miniature flexible instrument with unfolding and decoupling design for endoscopic surgery. IEEE Robot Autom Lett 9(1):787–794. https://doi.org/10.1109/LRA.2023.3336492 - DOI
    1. Chiu PWY, Ho KY, Phee SJ (2021) Colonic endoscopic submucosal dissection using a novel robotic system (with video). Gastrointest Endosc 93(5):1172–1177. https://doi.org/10.1016/j.gie.2020.09.042 - DOI - PubMed
    1. Pakhomov D, Premachandran V, Allan M, Azizian M, Navab N (2019) Deep Residual Learning for Instrument Segmentation in Robotic Surgery. In: Suk HI, Liu M, Yan P, Lian C, eds. Machine Learning in Medical Imaging. MLMI 2019. Vol 11861. Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-030-32692-0_65 .
    1. Lin S, Qin F, Peng H, Bly RA, Moe KS, Hannaford B (2021) Multi-frame feature aggregation for real-time instrument segmentation in endoscopic video. IEEE Robot Autom Lett 6(4):6773–6780. https://doi.org/10.1109/LRA.2021.3096156 - DOI

LinkOut - more resources