Abstract
Biomedical robotics has had a significant impact on flexible ureteroscopy (FURS) for the management of nephrolithiasis. The biomedical robots provide a suitable and safe platform for FURS. However, operating the robots expertly still represents a challenge for surgeons. Vision-based navigation is an effective means to simplify the operations of robots by surgeons, which has great potential to improve surgical efficiency. To achieve vision-based navigation, the localization of kidney stones in endoscopic images is the first step. In this paper, we propose a stone segmentation method (SSM) based on zero-shot learning, which consists of segmentation anything model (SAM), an image preprocessing module, and a mask postprocessing module. The SAM segments all objects in endoscopic images, which lack semantic information. The preprocessing module is designed to suppress interference of reflective area in endoscopic images, and the mask postprocessing module is used to filter noise masks. The experimental results on our collected endoscopic images indicate that our method achieves close accuracy on stone segmentation compared with supervised U-Net and VGG_U-Net, which significantly outperforms the Ostu and the SAM.
H. Meng and L. Chen—Contributed equally to this work.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aron, M., Haber, G.P., Desai, M.M., Gill, I.S.: Flexible robotics: a new paradigm. Curr. Opin. Urol. 17(3), 151–155 (2007)
Desai, M.M., et al.: Flexible robotic retrograde renoscopy: description of novel robotic device and preliminary laboratory experience. Urology 72(1), 42–46 (2008)
Desai, M.M., et al.: Robotic flexible ureteroscopy for renal calculi: initial clinical experience. J. Urol. 186(2), 563–568 (2011)
Doizi, S., Traxer, O.: Flexible ureteroscopy: technique, tips and tricks. Urolithiasis 46, 47–58 (2018)
Elkoushy, M.A., Andonian, S.: Prevalence of orthopedic complaints among endourologists and their compliance with radiation safety measures. J. Endourol. 25(10), 1609–1613 (2011)
Healy, K.A., Pak, R.W., Cleary, R.C., Colon-Herdman, A., Bagley, D.H.: Hand problems among endourologists. J. Endourol. 25(12), 1915–1920 (2011)
Holden, T., Pedro, R.N., Hendlin, K., Durfee, W., Monga, M.: Evidence-based instrumentation for flexible ureteroscopy: a review. J. Endourol. 22(7), 1423–1426 (2008)
Jiao, S., Li, X., Lu, X.: An improved OSTU method for image segmentation. In: 2006 8th International Conference on Signal Processing, vol. 2. IEEE (2006)
Kirillov, A., et al.: Segment anything (2023). arXiv:2304.02643
Li, R., et al.: Endoscopic segmentation of kidney stone based on transfer learning. In: 2021 40th Chinese Control Conference (CCC), pp. 8145–8150 (2021). https://doi.org/10.23919/CCC52363.2021.9550652
Marien, T., Mass, A.Y., Shah, O.: Antimicrobial resistance patterns in cases of obstructive pyelonephritis secondary to stones. Urology 85(1), 64–68 (2015). https://doi.org/10.1016/j.urology.2014.10.007
Monga, M., Dretler, S.P., Landman, J., Slaton, J.W., Conradie, M.C., Clayman, R.V.: Maximizing ureteroscope deflection: “play it straight’’. Urology 60(5), 902–905 (2002)
Rassweiler, J., Safi, K., Subotic, S., Teber, D., Frede, T.: Robotics and telesurgery-an update on their position in laparoscopic radical prostatectomy. Minim. Invasive Ther. Allied Technol. 14(2), 109–122 (2005)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015, Part III. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Saglam, R., Kabakci, A.S., Koruk, E., Tokatli, Z.: How did we designed and improved a new Turkish robot for flexible ureterorenoscope. J. Endourol. 26, A275–A275 (2012)
Saglam, R., et al.: A new robot for flexible ureteroscopy: development and early clinical results (IDEAL stage 1–2b). Eur. Urol. 66(6), 1092–1100 (2014). https://doi.org/10.1016/j.eururo.2014.06.047
Acknowledgements
The authors would like to acknowledge the support from the Scientific Research Item of Zhejiang Lab under Grant No. 2022NB0AC01.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Meng, H. et al. (2023). Zero-Shot Kidney Stone Segmentation Based on Segmentation Anything Model for Robotic-Assisted Endoscope Navigation. In: Yang, H., et al. Intelligent Robotics and Applications. ICIRA 2023. Lecture Notes in Computer Science(), vol 14269. Springer, Singapore. https://doi.org/10.1007/978-981-99-6489-5_7
Download citation
DOI: https://doi.org/10.1007/978-981-99-6489-5_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6488-8
Online ISBN: 978-981-99-6489-5
eBook Packages: Computer ScienceComputer Science (R0)