Skip to main content
SpringerLink
Log in

A Multi-Element Identification System Based on Deep Learning for the Visual Field of Percutaneous Endoscopic Spine Surgery

  • Original Article
  • Published:
Indian Journal of Orthopaedics Aims and scope Submit manuscript

Abstract

Background

Lumbar disc herniation is a common degenerative lumbar disease with an increasing incidence. Percutaneous endoscopic lumbar discectomy can treat lumbar disc herniation safely and effectively with a minimally invasive procedure. However, the learning curve of this technology is steep, which means that initial learners are often not sufficiently proficient in endoscopic operations, which can easily lead to iatrogenic damage. At present, the application of computer deep learning technology to clinical diagnosis, treatment, and surgical navigation has achieved satisfactory results.

Purpose

The objective of our team is to develop a multi-element identification system for the visual field of endoscopic spine surgery using deep learning algorithms and to evaluate the feasibility of this system.

Method

We established an image database by collecting surgical videos of 48 patients diagnosed with lumbar disc herniation, which was labeled by two spinal surgeons. We selected 6000 images of the visual field of percutaneous endoscopic spine surgery (including various tissue structures and surgical instruments), divided into the training data, validation data, and test data according to 2:1:2. We developed convolutional neural network models based on instance segmentation—Solov2, CondInst, Mask R-CNN and Yolact, and set the four network model backbone as ResNet101 and ResNet50 respectively. Mean average precision (mAP) and frames per second (FPS) were used to measure the performance of each model for classification, localization and recognition in real time, and AP (average) is used to evaluate how easily an element is detected by neural networks based on computer deep learning.

Result

Comprehensively comparing mAP and FSP of each model for bounding box test and segmentation task for the test set of images, we found that Solov2 (ResNet101) (mAP = 73.5%, FPS = 28.9), Mask R-CNN (ResNet101) (mAP = 72.8%, FPS = 28.5) models are the most stable, with higher precision and faster image processing speed. Combining the average precision of the elements in the bounding box test and segmentation tasks in each network, the AP(average) was highest for tool 3 (bbox-0.85, segm-0.89) and lowest for tool 5 (bbox-0.63, segm-0.72) in the instrumentation, whereas in the anatomical tissue elements, the fibrosus annulus (bbox-0.68, segm-0.69) and ligamentum flavum (bbox-0.65, segm-0.62) had higher AP(average),while extra-dural fat (bbox-0.42, segm-0.44) was lowest.

Conclusion

Our team has developed a multi-element identification system for the visual field of percutaneous endoscopic spine surgery adapted to the interlaminar and foraminal approaches, which can identify and track anatomical tissue (nerve, ligamentum flavum, nucleus pulposus, etc.) and surgical instruments (endoscopic forceps, an high-speed diamond burr, etc.), which can be used in the future as a virtual educational tool or applied to the intraoperative real-time assistance system for spinal endoscopic operation.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Availability of Data and Materials

The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author/s.

References:

  1. Zhang, A. S., Xu, A., Ansari, K., Hardacker, K., Anderson, G., Alsoof, D., & Daniels, A. H. (2023). Lumbar Disc Herniation: Diagnosis and Management. American Journal of Medicine, 136, 645–651. https://doi.org/10.1016/j.amjmed.2023.03.024

    Article  PubMed  Google Scholar 

  2. Shen, S. C., Chen, H. C., Tsou, H. K., Lin, R. H., Shih, Y. T., Huang, C. W., Tang, C. L., Chen, H. T., Chang, C. C., & Tzeng, C. Y. (2023). Percutaneous endoscopic lumbar discectomy for L5–S1 disc herniation based on image analysis and clinical findings: A retrospective review of 345 cases. Medicine (Baltimore), 102, e32832. https://doi.org/10.1097/MD.0000000000032832

    Article  PubMed  Google Scholar 

  3. Pan, M., Li, Q., Li, S., Mao, H., Meng, B., Zhou, F., & Yang, H. (2020). Percutaneous endoscopic lumbar discectomy: Indications and complications. Pain Physician, 23, 49–56.

    CAS  PubMed  Google Scholar 

  4. Cheng, Y. P., Cheng, X. K., & Wu, H. (2022). A comparative study of percutaneous endoscopic interlaminar discectomy and transforaminal discectomy for L5–S1 calcified lumbar disc herniation. BMC Musculoskeletal Disorders, 23, 244. https://doi.org/10.1186/s12891-022-05186-z

    Article  PubMed  PubMed Central  Google Scholar 

  5. Ahn, Y., Lee, S., Son, S., Kim, H., & Kim, J. E. (2020). Learning curve for transforaminal percutaneous endoscopic lumbar discectomy: A systematic review. World Neurosurgery, 143, 471–479. https://doi.org/10.1016/j.wneu.2020.08.044

    Article  PubMed  Google Scholar 

  6. Ao, S., Wu, J., Tang, Y., Zhang, C., Li, J., Zheng, W., & Zhou, Y. (2019). Percutaneous endoscopic lumbar discectomy assisted by O-arm-based navigation improves the learning curve. BioMed Research International, 2019, 6509409. https://doi.org/10.1155/2019/6509409

    Article  PubMed  PubMed Central  Google Scholar 

  7. Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L. H., & Aerts, H. (2018). Artificial intelligence in radiology. Nature Reviews Cancer, 18, 500–510. https://doi.org/10.1038/s41568-018-0016-5

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Yeh, Y. C., Weng, C. H., Huang, Y. J., Fu, C. J., Tsai, T. T., & Yeh, C. Y. (2021). Deep learning approach for automatic landmark detection and alignment analysis in whole-spine lateral radiographs. Science and Reports, 11, 7618. https://doi.org/10.1038/s41598-021-87141-x

    Article  CAS  Google Scholar 

  9. Fan, N., Yuan, S., Du, P., Zhu, W., Li, L., Hai, Y., Ding, H., Wang, G., & Zang, L. (2020). Design of a robot-assisted system for transforaminal percutaneous endoscopic lumbar surgeries: Study protocol. Journal of Orthopaedic Surgery and Research, 15, 479. https://doi.org/10.1186/s13018-020-02003-y

    Article  PubMed  PubMed Central  Google Scholar 

  10. Hagan, M. J., Remacle, T., Leary, O. P., Feler, J., Shaaya, E., Ali, R., Zheng, B., Bajaj, A., Traupe, E., Kraus, M., et al. (2022). Navigation Techniques in Endoscopic Spine Surgery. BioMed Research International, 2022, 8419739. https://doi.org/10.1155/2022/8419739

    Article  PubMed  PubMed Central  Google Scholar 

  11. Fan, N., Yuan, S., Du, P., Wu, Q., Wang, T., Wang, A., Li, J., Kong, X., Zhu, W., & Zang, L. (2021). Complications and risk factors of percutaneous endoscopic transforaminal discectomy in the treatment of lumbar spinal stenosis. BMC Musculoskeletal Disorders, 22, 1041. https://doi.org/10.1186/s12891-021-04940-z

    Article  PubMed  PubMed Central  Google Scholar 

  12. Fan, G., Liu, H., Wang, D., Feng, C., Li, Y., Yin, B., Zhou, Z., Gu, X., Zhang, H., Lu, Y., et al. (2020). Deep learning-based lumbosacral reconstruction for difficulty prediction of percutaneous endoscopic transforaminal discectomy at L5/S1 level: A retrospective cohort study. International Journal of Surgery, 82, 162–169. https://doi.org/10.1016/j.ijsu.2020.08.036

    Article  PubMed  Google Scholar 

  13. Cui, P., Shu, T., Lei, J., & Chen, W. (2021). Nerve recognition in percutaneous transforaminal endoscopic discectomy using convolutional neural network. Medical Physics, 48, 2279–2288. https://doi.org/10.1002/mp.14822

    Article  PubMed  Google Scholar 

  14. Cho, S. M., Kim, Y. G., Jeong, J., Kim, I., Lee, H. J., & Kim, N. (2021). Automatic tip detection of surgical instruments in biportal endoscopic spine surgery. Computers in Biology and Medicine, 133, 104384. https://doi.org/10.1016/j.compbiomed.2021.104384

    Article  PubMed  Google Scholar 

  15. Lokhande, P. V. (2023). Full endoscopic spine surgery. Journal of Orthopaedics, 40, 74–82. https://doi.org/10.1016/j.jor.2023.04.010

    Article  PubMed  Google Scholar 

  16. Zhang, Y., Chu, J., Leng, L., & Miao, J. (2020). Mask-refined R-CNN: a network for refining object details in instance segmentation. Sensors (Basel). https://doi.org/10.3390/s20041010

    Article  PubMed  PubMed Central  Google Scholar 

  17. He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2020). Mask R-CNN. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42, 386–397. https://doi.org/10.1109/TPAMI.2018.2844175

    Article  PubMed  Google Scholar 

  18. Wang, N., Zhang, J., & Song, X. (2023). A pipeline defect instance segmentation system based on SparseInst. Sensors (Basel). https://doi.org/10.3390/s23229019

    Article  PubMed  PubMed Central  Google Scholar 

  19. Bolya, D., Zhou, C., Xiao, F., & Lee, Y. J. (2022). YOLACT++ better real-time instance segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 1108–1121. https://doi.org/10.1109/TPAMI.2020.3014297

    Article  PubMed  Google Scholar 

  20. Yu, Z., Liu, L., Jiao, H., Chen, J., Chen, Z., Song, Z., Lin, H., & Tian, F. (2022). Leveraging SOLOv2 model to detect heat stress of poultry in complex environments. Frontiers in Veterinary Science, 9, 1062559. https://doi.org/10.3389/fvets.2022.1062559

    Article  PubMed  Google Scholar 

  21. Alaeddine, H., & Jihene, M. (2021). Deep residual network in network. Computational Intelligence and Neuroscience, 2021, 6659083. https://doi.org/10.1155/2021/6659083

    Article  PubMed  PubMed Central  Google Scholar 

  22. Reiner, A. J., Hollands, J. G., & Jamieson, G. A. (2017). Target detection and identification performance using an automatic target detection system. Human Factors, 59, 242–258. https://doi.org/10.1177/0018720816670768

    Article  PubMed  Google Scholar 

  23. Zarvani, M., Saberi, S., Azmi, R., & Shojaedini, S. V. (2021). Residual learning: a new paradigm to improve deep learning-based segmentation of the left ventricle in magnetic resonance imaging cardiac images. Journal of Medical Signals and Sensors, 11, 159–168. https://doi.org/10.4103/jmss.JMSS_38_20

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

Thank you for all the support from the XuZhou Central Hospital and Xuzhou Medical University.

Funding

This study was supported by the Projects of Medical Key and leading talents of Xuzhou (XWRCHT20220050, XWRCHT20210035), Xuzhou Plan of introducing a team of clinical medical experts(2019TD002), the Project of Health Innovation Teams of Xuzhou (XWCX201601), Xuzhou Medical Foundation for Youth Reserved Experts Fund (2014006), Jiangsu Provincial Medical Youth Talent (QNRC2016392), the Scientific Research Projects of Jiangsu Provincial Health Commission (M2022048, Z2022040), “Six one Projects” for High-level Health Talents in Jiangsu Province (LGY2018047), Jiangsu Province “333” talents Project, The Project of Science and Technology of Xuzhou (KC22161), Postdoctoral Project of China (314233).

Author information

Author notes

  1. Jinhui Bu, Yan Lei and Yari Wang contributed equally to this work.

Authors and Affiliations

  1. Affiliated Xuzhou Clinical College of Xuzhou Medical University, Xuzhou, 221009, China

    Jinhui Bu, Yan Lei, Sen Huang, Bo He, Minghui Dong, Chao Ma & Guangwang Liu

  2. School of Computer Science, China University of Mining and Technology, Xuzhou, 221116, China

    Yari Wang & Jiaqi Zhao

  3. Department of Orthopedic Surgery, Xuzhou Central Hospital, Xuzhou Central Hospital Affiliated to Nanjing University of Chinese Medicine, The Xuzhou School of Clinical Medicine of Nanjing Medical University, Xuzhou Central Hospital Affiliated to Medical School of Southeast University, Xuzhou, 221009, China

    Jun Liang, Zhenfei Wang, Guangpu Liu, Ru Niu, Chao Ma & Guangwang Liu

  4. Bengbu Medical College, Bengbu, 233000, China

    Long Xu

Authors
  1. Jinhui Bu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yan Lei
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yari Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jiaqi Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Sen Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jun Liang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Zhenfei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Long Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Bo He
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Minghui Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Guangpu Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Ru Niu
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Chao Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Guangwang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

JHB, YRW, JQZ and GWL contributed to conception and design of the study. JHB, SH, JL, ZFW and LX organized the database. JHB, YL, BH, MHD and GPL performed the statistical analysis. JHB, RN, CM and GWL wrote the first draft of the manuscript. JHB, YL, CM were involved in article revisions. All authors read and approved the final manuscript.

Corresponding authors

Correspondence to Chao Ma or Guangwang Liu.

Ethics declarations

Conflict of Interest

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Ethics Approval and Consent to Participate

This study was approved by the Ethics Review Committee of Xuzhou Central Hospital under the ethical number XZXY-LK-20221020-095, in accordance with the Declaration of Helsinki. The patients/participants provided their written informed consent to participate in this study. Written informed consent was obtained from the individual(s) for the publication of any potentially identifiable images or data included in this article.

Consent for Publication

All authors contributed to the article and approved the submitted version.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bu, J., Lei, Y., Wang, Y. et al. A Multi-Element Identification System Based on Deep Learning for the Visual Field of Percutaneous Endoscopic Spine Surgery. JOIO 58, 587–597 (2024). https://doi.org/10.1007/s43465-024-01134-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s43465-024-01134-2

Keywords

Search

Navigation