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 Jul 30;15(15):1917.
doi: 10.3390/diagnostics15151917.

DeepVinci: Organ and Tool Segmentation with Edge Supervision and a Densely Multi-Scale Pyramid Module for Robot-Assisted Surgery

Li-An Tseng  1 , Yuan-Chih Tsai  2 , Meng-Yi Bai  3   4 , Mei-Fang Li  3   4 , Yi-Liang Lee  5   6 , Kai-Jo Chiang  7   8 , Yu-Chi Wang  5 , Jing-Ming Guo  1
Affiliations

DeepVinci: Organ and Tool Segmentation with Edge Supervision and a Densely Multi-Scale Pyramid Module for Robot-Assisted Surgery

Li-An Tseng et al. Diagnostics (Basel). .

Abstract

Background: Automated surgical navigation can be separated into three stages: (1) organ identification and localization, (2) identification of the organs requiring further surgery, and (3) automated planning of the operation path and steps. With its ideal visual and operating system, the da Vinci surgical system provides a promising platform for automated surgical navigation. This study focuses on the first step in automated surgical navigation by identifying organs in gynecological surgery. Methods: Due to the difficulty of collecting da Vinci gynecological endoscopy data, we propose DeepVinci, a novel end-to-end high-performance encoder-decoder network based on convolutional neural networks (CNNs) for pixel-level organ semantic segmentation. Specifically, to overcome the drawback of a limited field of view, we incorporate a densely multi-scale pyramid module and feature fusion module, which can also enhance the global context information. In addition, the system integrates an edge supervision network to refine the segmented results on the decoding side. Results: Experimental results show that DeepVinci can achieve state-of-the-art accuracy, obtaining dice similarity coefficient and mean pixel accuracy values of 0.684 and 0.700, respectively. Conclusions: The proposed DeepVinci network presents a practical and competitive semantic segmentation solution for da Vinci gynecological surgery.

Keywords: artificial intelligence; da Vinci Robot; deep learning; gynecological surgery; organ semantic segmentation.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 4
Figure 4
Overall framework of the proposed FFM.
Figure 5
Figure 5
Proposed edge supervision network.
Figure 1
Figure 1
Top: Initial images. Bottom: Image annotation obtained by drawing contours of organs for the following classes: uterus (green), ovary (blue), uterine tube (cyan), colon (yellow), myoma (red), ovarian tumor (magenta), and tool (gray).
Figure 2
Figure 2
Overall framework of the proposed DeepVinci.
Figure 3
Figure 3
Overall architecture of the proposed DMPM. D: Dilation rate.
Figure 6
Figure 6
Organ detection by each model. Our DeepVinci model successfully detected the uterus, ovary, uterine tube, colon, myoma, ovarian tumor, and tool.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Reich H., Decaprio J., McGlynn F. Laparoscopic hysterectomy. J. Gynecol. Surg. 1989;5:213–216. doi: 10.1089/gyn.1989.5.213. - DOI
    1. Lavoue V., Collinet P., Fernandez H. Robotic Surgery in Gynecology: Has France Lost Its Leadership in Minimally Invasive Surgery? Volume 49. Elsevier; Amsterdam, The Netherlands: 2020. p. 101708. - DOI - PubMed
    1. Martin R.F., Clinics S. Robotic surgery. Surg. Clin. 2020;100:xiii–xiv. doi: 10.1016/j.suc.2020.02.001. - DOI - PubMed
    1. Seamon L.G., Cohn D.E., Henretta M.S., Kim K.H., Carlson M.J., Phillips G.S., Fowler J.M. Minimally invasive comprehensive surgical staging for endometrial cancer: Robotics or laparoscopy? Gynecol. Oncol. 2009;113:36–41. doi: 10.1016/j.ygyno.2008.12.005. - DOI - PubMed
    1. Sarikaya D., Corso J.J., Guru K.A. Detection and localization of robotic tools in robot-assisted surgery videos using deep neural networks for region proposal and detection. IEEE Trans. Med. Imaging. 2017;36:1542–1549. doi: 10.1109/TMI.2017.2665671. - DOI - PubMed

LinkOut - more resources