Abstract
Purpose
Pedicle screw fixation is a challenging procedure with a concerning rates of reoperation. After insertion of the screws is completed, the most common intraoperative verification approach is to acquire anterior–posterior and lateral radiographic images, based on which the surgeons try to visually assess the correctness of insertion. Given the limited accuracy of the existing verification techniques, we identified the need for an accurate and automated pedicle screw assessment system that can verify the screw insertion intraoperatively. For doing so, this paper offers a framework for automatic segmentation and pose estimation of pedicle screws based on deep learning principles.
Methods
Segmentation of pedicle screw X-ray projections was performed by a convolutional neural network. The network could isolate the input X-rays into three classes: screw head, screw shaft and background. Once all the screw shafts were segmented, knowledge about the spatial configuration of the acquired biplanar X-rays was used to identify the correspondence between the projections. Pose estimation was then performed to estimate the 6 degree-of-freedom pose of each screw. The performance of the proposed pose estimation method was tested on a porcine specimen.
Results
The developed machine learning framework was capable of segmenting the screw shafts with 93% and 83% accuracy when tested on synthetic X-rays and on clinically realistic X-rays, respectively. The pose estimation accuracy of this method was shown to be \(1.93^{\circ } \pm 0.64^{\circ }\) and \(1.92 \pm 0.55\,\hbox {mm}\) on clinically realistic X-rays.
Conclusions
The proposed system offers an accurate and fully automatic pedicle screw segmentation and pose assessment framework. Such a system can help to provide an intraoperative pedicle screw insertion assessment protocol with minimal interference with the existing surgical routines.
Similar content being viewed by others
References
Heim SE (1997) Transpedicle instrumentation in the degenerative spine. Clin Orthop Relat Res 337:97–110
Katonis P, Christoforakis J, Aligizakis AC, Papadopoulos C, Sapkas G, Hadjipavlou A (2003) Complications and problems related to pedicle screw fixation of the spine. Clin Orthop Relat Res 411:86–94
Ackbas SC, Arslan FY, Tuncer MR (2003) The effect of transpedicular screw misplacement on late spinal stability. Acta Neurochir 145:949–955
Gelalis ID, Paschos NK, Pakos EE, Politis AN, Arnaoutoglou CM, Karageorgos AC, Ploumis A, Xenakis TA (2011) Accuracy of pedicle screw placement: a systematic review of prospective in vivo studies comparing free hand, fluoroscopy guidance and navigation techniques. Eur Spine J 21:247–255
Amato V, Giannachi L, Irace C, Corona C (2010) Accuracy of pedicle screw placement in the lumbosacral spine using conventional technique: computed tomography postoperative assessment in 102 consecutive patients: Clinical article. J Neurosurg Spine 12:306–313
Gertzbein SD, Robbins S (1990) Accuracy of pedicular screw placement in vivo. Spine 15:11–14
Allam Y, Silbermann J, Riese F, Greiner-Perth R (2013) Computer tomography assessment of pedicle screw placement in thoracic spine: comparison between free hand and a generic 3D-based navigation techniques. Eur Spine J 22:648–653
Chiang CF, Tsai TT, Chen LH, Lai PL, Fu TS, Niu CC, Chen WJ (2012) Computed tomography-based navigation-assisted pedicle screw insertion for thoracic and lumbar spine fractures. Chang Gung Med J 35:332–338
Choma TJ, Denis F, Lonstein JE, Perra JH, Schwender JD, Garvey TA, Mullin WJ (2006) Stepwise methodology for plain radiographic assessment of pedicle screw placement: a comparison with computed tomography. J Spinal Disord Tech 19:547–553
Cordemans V, Kaminski L, Banse X, Francq BG, Cartiaux O (2017) Accuracy of a new intraoperative cone beam CT imaging technique (Artis Zeego II) compared to postoperative CT scan for assessment of pedicle screws placement and breaches detection. Eur Spine J 26:2906–2916
Newell R, Esfandiari H, Anglin C, Bernard R, Street J, Hodgson AJ (2018) An Intraoperative Fluoroscopic Method to Accurately Measure the Post-implantation Position of Pedicle Screws. Int J Comput Assist Radiol Surg. https://doi.org/10.1007/s11548-018-1732-8
Markelj P, Tomazevic D, Likar B, Pernus F (2012) A review of 3D/2D registration methods for image-guided interventions. Med Image Anal 16:642–661
Otake Y, Schafer S, Stayman JW, Zbijewski W, Kleinszig G, Graumann R, Khanna AJ, Siewerdsen JH (2012) Automatic localization of vertebral levels in x-ray fluoroscopy using 3D–2D registration: a tool to reduce wrong-site surgery. Phys Med Biol 57:5485–5508
Varnavas A, Carrell T, Penney G (2015) Fully automated 2D–3D registration and verification. Med Image Anal 26:108–119
Miao S, Wang ZJ, Liao R (2016) A CNN regression approach for real-time 2D/3D registration. IEEE Trans Med Imaging 35:1352–1363
Popescu D, Amza CG, Laptoiu D, Amza G (2012) Competitive hopfield neural network model for evaluating pedicle Screw placement accuracy. Stroj vestn J Mech Eng 58:509–516
Uneri A, De Silva T, Goerres J, Jacobson M, Ketcha M, Reaungamornrat S, Kleinszig G, Vogt S, Khanna A, Osgood G, Wolinsky JP, Siewerdsen J (2017) Intraoperative evaluation of device placement in spine surgery using known-component 3D–2D image registration. Phys Med Biol 62:3330–3351
Navab N, Bani-Hashemi AR, Mitschke MM, Holdsworth DW, Fahrig R, Fox AJ, Graumann R (1996) Dynamic geometrical calibration for 3D cerebral angiography. In: SPIE—The International Society for Optical Engineering. International Society for Optics and Photonics, pp 361–370
Chintalapani G, Jain AK, Burkhardt DH, PrinceJL, Fichtinger G (2008) CTREC: C-arm tracking and reconstruction using elliptic curves. In: Conference on computer vision and pattern recognition workshops. IEEE, pp 1–7
Schumann S, Thelen B, Ballestra S, Nolte LP, Bchler P, Zheng G (2014) X-ray image calibration and its application to clinical orthopedics. Med Eng Phys 36:968–974
Amiri S, Wilson DR, Masri BA, Anglin C (2014) A low-cost tracked C-arm (TC-arm) upgrade system for versatile quantitative intraoperative imaging. Int J CARS 9:695–711
Esfandiari H, Martinez JF, Gonzlez Ivarez A, Guy P, Street J, Anglin C, Hodgson AJ (2017) An automatic, robust and closed form mini-RSA system for intraoperative C-arm calibration. Int J Comput Assist Radiol Surg 12(Suppl 1):S37–S38
Abdel-Aziz YI, Karara HM (1971). Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry. In: Proceedings of the American society of photogrammetry symposium on close-range photogrammetry, Washington, DC, 1-18. ASP, Falls Church, VA
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440
Vedaldi A, Lenc K (2015) MatConvNet: convolutional neural networks for MATLAB. In: Proceedings of the 23rd ACM international conference on multimedia, ACM Press, Brisbane, Australia, pp 689–692
Seroul P, Sarrut D (2008) VV: A viewer for the evaluation of 4D image registration. In: MIDAS Journal (Medical image computing and computer-assisted intervention MICCAI2008, workshop-systems and architectures for computer assisted interventions), p 18
Haough Paul VC(1962) Method and means for recognizing complex patterns. Patent number: US3069654 A
Acknowledgements
This work has been supported by the Canadian Natural Sciences and Engineering Research Council (NSERC) and the Canadian Institutes of Health Research (CIHR). We thank the Centre for Hip Health and Mobility for providing the laboratory facilities used in this study and the Institute for Computing, Information and Cognitive Systems for program support.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest
Ethical approval
All procedures performed in studies involving animals were in accordance with the ethical standards of the institution or practice at which the studies were conducted
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Esfandiari, H., Newell, R., Anglin, C. et al. A deep learning framework for segmentation and pose estimation of pedicle screw implants based on C-arm fluoroscopy. Int J CARS 13, 1269–1282 (2018). https://doi.org/10.1007/s11548-018-1776-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-018-1776-9