skip to main content
10.1145/3644116.3644359acmotherconferencesArticle/Chapter ViewAbstractPublication PagesisaimsConference Proceedingsconference-collections
research-article

A Gastrointestinal Endoscope Navigation Method with PoseLSTM Combining improved attention mechanisms

Published: 05 April 2024 Publication History

Abstract

To address the issues of high cost and lack of miniaturization in traditional gastrointestinal endoscope navigation systems, this paper proposes an end-to-end monocular visual localization system. The system employs PoseLSTM to implement gastrointestinal endoscope navigation and integrates Self-CBAM to enhance system robustness and accuracy. The Self-CBAM module conducts channel attention weighting and spatial attention weighting on the input feature map, enabling the model to focus on important features. Additionally, the module increases the model's nonlinearity, thereby improving the accuracy of position and pose regression. Compared to the original model, the proposed method achieves higher accuracy, with a median translational error of 1.1467mm and a median rotational error of 5.502°.

References

[1]
Cui X W, Chen W, Han B X Virtual endoscopy image-enhanced navigation system for knee arthroscopic surgery [J]. Chinese Journal of Biomedical Engineering, 2019, 38(05):558-565.
[2]
Yang, S., Wang, S., & Shen, S. 2019. Visual Localization for Mobile Robots: A Survey. IEEE Transactions on Robotics, 35(4), 901-916.
[3]
Wang P, Xiao X, Glissen Brown JR, Automatic polyp detection in colonoscopy images using CNN and handcrafted features. IEEE Trans Med lmaging 2018: 37(5):1198-209. DO:10.1109/TM1.2017.2788160.
[4]
Wang Y, Wang Y, Zhang X, Endoscopic navigation system for precise biopsy of gastric submucosal tumors Endoscopic navigation system for precise biopsy of gastric submucosal tumors. Surg Endosc 2019: 33(7):2325-33DO1:101007/s00464-018-6245-0.
[5]
Wang Y, Wang Y, Zhang X, Development and clinical application of a novel endoscopic navigation system based on an electromagnetic tracking method Development and clinical application of a novel endoscopic navigation system based on an electromagnetic tracking method. J Surg Res 2021: 262:1-8. DOl:10.1016/ijss.2020.12.048.
[6]
Zhang, Y., Liu, Y. 2020. End-to-End Monocular Visual Localization: A Review. IEEE Access, 8, 174, 042-174, 062.
[7]
Kendall, A., Grimes, M., & Cipolla, R. 2015. PoseNet: A convolutional network for real-time 6-dof camera relocalization. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2938-2946).
[8]
Sunderhauf, N., Shirazi, S., & Dayoub, F. 2017. Image based localization using LSTMs for structured feature correlation. In Proceedings of the IEEE International Conference on Robotics and Automation (pp. 1188-1195).
[9]
Shuster, M. D. 2016. A survey of attitude representations. The Journal of the Astronautical Sciences, 64(4), 419-473.
[10]
Rafael C. Gonzalez, Richard E. Woods. Digital Image Processing (fourth edition) [M]. Translated by Ruan Q Q, Ruan Y Z. Beijing: Publishing House of Electronics Industry, 2020.
[11]
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., … & Rabinovich, A. 2015. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1-9).
[12]
He K M, Zhang X Y, Ren S Q, Deep Residual Learning for Image Recognition [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recogniztion. Washington, DC, USA: IEEE Computer Society, 2016: 770-7785.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ISAIMS '23: Proceedings of the 2023 4th International Symposium on Artificial Intelligence for Medicine Science
October 2023
1394 pages
ISBN:9798400708138
DOI:10.1145/3644116
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 05 April 2024

Permissions

Request permissions for this article.

Check for updates

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

ISAIMS 2023

Acceptance Rates

Overall Acceptance Rate 53 of 112 submissions, 47%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 7
    Total Downloads
  • Downloads (Last 12 months)7
  • Downloads (Last 6 weeks)1
Reflects downloads up to 20 Jan 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media