Abstract
Computed tomography (CT) imaging is a cornerstone of modern orthopedic practice due to unmatched clarity in its volumetric reconstruction of internal bony anatomy. However, CT imaging carries the risk of elevated radiation exposure, is costly to acquire, and in certain situations is simply unavailable. While in the operating room, for instance, at a time when the information it can provide is arguably most needed, surgeons do not typically have access to CT. Instead, they must rely on 2D fluoroscopic imaging to visualize complex internal anatomy. Here, we present a method to accurately reconstruct bony anatomy from sparse fluoroscopy sampling (as few as 7 input views) in under 30 s by leveraging a recent advancement in computer vision/machine learning known as neural radiance fields, or NeRFs. Using two different surgical applications, we then demonstrate how the method performs given a variety of input fluoroscopy views, both in terms of the time it takes to reconstruct bony anatomy and the accuracy of the reconstruction. Based on these initial findings, we conclude that this method shows promise for use in the operating room as an adjunct to conventional intra-operative imaging capabilities.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gelalis, I.D., et al.: 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(2), 247–255 (2012)
Garner, M.R., et al.: Standard perioperative imaging modalities are unreliable in assessing articular congruity of ankle fractures. J. Orthop. Trauma 29(4), 161–165 (2015)
Büchler, L., et al.: Reliability of radiologic assessment of the fracture anatomy at the posterior tibial plafond in malleolar fractures. J. Orthop. Trauma 23(3), 208–212 (2009)
Ebraheim, N., Sabry, F.F., Mehalik, J.N.: Intraoperative imaging of the tibial plafond fracture: a potential pitfall. Foot Ankle Int. 21(1), 67–72 (2000)
Borrelli, J., et al.: Assessment of articular fragment displacement in acetabular fractures: a comparison of computerized tomography and plain radiographs. J. Orthop. Trauma 16(7), 449–456 (2002)
Müller, T., et al.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. 41(4), 1–15 (2022)
Vedaldi, A., et al.: NeRF: representing scenes as neural radiance fields for view synthesis. arXiv:2003.08934 (2020)
Gao, K., et al., NeRF: neural radiance field in 3d vision, a comprehensive review. arXiv:2210.00379 (2022)
Rabby, A.K.M.S.A., Zhang, C.: BeyondPixels: a comprehensive review of the evolution of neural radiance fields. arXiv:2306.03000 (2023)
Wysocki, M., et al.: Ultra-NeRF: neural radiance fields for ultrasound imaging. arXiv:2301.10520 (2023)
Chen, Q.Y.: 3D reconstruction of endoscopy images with NeRF. dissertation, New York University Tandon School of Engineering (2023)
Rückert, D., et al.: NeAT: neural adaptive tomography. ACM Trans. Graph. 41(4), 1–13 (2022)
Chen, S., Williams, L.: View interpolation for image synthesis. In: International Conference on Computer Graphics and Interactive Techniques, pp. 279–288. Association for Computing Machinery, New York, New York (1993)
Wellington, S.L., Vinegar, H.J.J.: X-ray computerised tomography. Int. J. Rock Mech. Min. Sci. Geomechanics Abstracts 25(2), 57 (1987)
Moore, C.S., et al.: A method to produce and validate a digitally reconstructed radiograph-based computer simulation for optimisation of chest radiographs acquired with a computed radiography imaging system. Br. J. Radiol. 84(1006), 890–902 (2011)
Dorgham, O.M., Laycock, S.D., Fisher, M.H.: GPU accelerated generation of digitally reconstructed radiographs for 2-D/3-D image registration. TBME 59(9), 2594–2603 (2012)
Haque, M.A., et al.: Hierarchical model-based tracking of cervical vertebrae from dynamic biplane radiographs. Med. Eng. Phys. 35(7), 994–1004 (2012)
Kern, A.M.: Intra-operative Biomechanical Analysis for Improvement of Intra-articular Fracture Reduction. Dissertation, University of Iowa (2017)
Larobina, M., Murino, L.: Medical image file formats. J. Digit. Imaging 27(2), 200–206 (2014)
Nelson, E.M.A., et al.: Intraoperative fluoroscopy, portable X-ray, and CT: patient and operating room personnel radiation exposure in spinal surgery. Spine J. 14(12), 2985–2991 (2014)
Su, A.W., et al.: How does patient radiation exposure compare with low-dose o-arm versus fluoroscopy for pedicle screw placement in idiopathic scoliosis? J. Pediatr. Orthop. 37(3), 171–177 (2017)
Huang, A.J., et al.: Using cone-beam CT as a low-dose 3D imaging technique for the extremities: initial experience in 50 subjects. Skeletal Radiol. 44(6), 797–809 (2015)
Tajsic, T., et al.: Spinal navigation for minimally invasive thoracic and lumbosacral spine fixation: implications for radiation exposure, operative time, and accuracy of pedicle screw placement. Eur. Spine J. 27(8), 1918–1924 (2018)
Heimann, T., Meinzer, H.P.: Statistical shape models for 3D medical image segmentation: a review. Med. Image Anal. 13(4), 543–563 (2009)
Zheng, G., et al.: Reconstruction of patient-specific 3D bone surface from 2D calibrated fluoroscopic images and point distribution model. In: Larsen, R., Nielsen, M., Sporring, J., Medical Image Computing and Computer-Assisted Intervention 2006, LNCS, vol. 4190, pp. 25–32. Springer, Heidelberg (2006). https://doi.org/10.1007/11866565_4
Shiode, R., Kabashima, M., Hiasa, Y., et al.: 2D–3D reconstruction of distal forearm bone from actual X-ray images of the wrist using convolutional neural networks. Sci. Rep. 11(1), 15249 (2021)
Ge, R., et al.: X-CTRSNet: 3D cervical vertebra CT reconstruction and segmentation directly from 2D X-ray images. Knowl.-Based Syst. 236, 107680 (2022)
von Landesberger, T., et al.: Opening up the “black box” of medical image segmentation with statistical shape models. Visual Computing 29(9), 893–905 (2013)
Willey, M.C., et al.: Biomechanical guidance can improve accuracy of reduction for intra-articular tibia plafond fractures and reduce joint contact stress. J. Orthop. Res.Orthop. Res. 41(3), 546–554 (2023)
Acknowledgements
This project was funded under grant #R18 HS025353 from the U.S. Agency for Healthcare Research and Quality.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Tatum, M., Thomas, G.W., Anderson, D.D. (2024). Reconstruction of Bony Anatomy from Sparse Fluoroscopy Sampling Using Neural Radiance Fields. In: Skalli, W., Laporte, S., Benoit, A. (eds) Computer Methods in Biomechanics and Biomedical Engineering II. CMBBE 2023. Lecture Notes in Computational Vision and Biomechanics, vol 39. Springer, Cham. https://doi.org/10.1007/978-3-031-55315-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-55315-8_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-55314-1
Online ISBN: 978-3-031-55315-8
eBook Packages: EngineeringEngineering (R0)