臨床整形外科57巻10号

2022年10月発行

特集 整形外科領域における人工知能の応用 各論

深層学習を用いた単純X線画像のみからの前腕遠位部3次元骨形状推定

著者： 塩出亮哉¹

所属機関： ¹大阪大学大学院医学系研究科整形外科

ページ範囲：P.1197 - P.1203

Computed tomography(CT)から生成する3次元骨モデルは臨床的有用性が高い一方で，骨モデルの作成にかかる多大なコストと労力，時間，さらには医療被曝が課題である．それらの課題を解決するために，単純X線画像から直接高精度な3次元骨モデルを推定構築するための深層学習ネットワークを開発した．健常成人の手関節のCT画像と単純X線画像のデータセットを用いるうえで，CTから生成する疑似X線画像を学習に用いることで，医用画像における問題点を解決した．

参考文献

1) Mavrogenis AF, Savvidou OD, Mimidis G, et al. Computer-assisted navigation in orthopedic surgery. Orthopedics 2013;36(8):631-42.

2) Murase T, Oka K, Moritomo H, et al. Three-dimensional corrective osteotomy of malunited fractures of the upper extremity with use of a computer simulation system. J Bone Joint Surg Am 2008;90(11):2375-89.

3) Ng VY, DeClaire JH, Berend KR, et al. Improved accuracy of alignment with patient-specific positioning guides compared with manual instrumentation in TKA. Clin Orthop Relat Res 2012;470(1):99-107.

4) Oka K, Tanaka H, Okada K, et al. Three-dimensional corrective osteotomy for malunited fractures of the upper extremity using patient-matched instruments:a prospective, multicenter, open-label, single-arm trial. J Bone Joint Surg Am 2019;101(8):710-21.

5) Sodickson A, Baeyens PF, Andriole KP, et al. Recurrent CT, cumulative radiation exposure, and associated radiation-induced cancer risks from CT of adults. Radiology 2009;251:175-84.

6) Baka N, Kaptein BL, de Bruijne M, et al. 2D-3D shape reconstruction of the distal femur from stereo X-ray imaging using statistical shape models. Med Image Anal 2011;15(6):840-50.

7) Yu W, Tannast M, Zheng G. Non-rigid free-form 2D-3D registration using a B-spline-based statistical deformation model. Pattern Recognition 2017;63:689-99.

8) Cerveri P, Sacco C, Olgiati G, et al. 2D/3D reconstruction of the distal femur using statistical shape models addressing personalized surgical instruments in knee arthroplasty:a feasibility analysis. Int J Med Robotics Comput Assist Surg 2017;13(4):e1823.

9) Yu W, Chu C, Tannast M, et al. Fully automatic reconstruction of personalized 3D volumes of the proximal femur from 2D X-ray images. Int J Comput Assist Radiol Surg 2016;11(9):1673-85.

10) Prakoonwit S. Towards multiple 3D bone surface identification and reconstruction using few 2D X-ray images for intraoperative applications. International Journal of Art, Culture and Design Technologies 2014;4(1):13-31.

11) Tulsiani S, Zhou T, Efros A, et al. Multi-view supervision for single-view reconstruction via differentiable ray consistency. IEEE Trans Pattern Anal Mach Intell 2019.

12) Henzler P, Rasche V, Ropinski T, Ritschel T. Single-image Tomography:3D Volumes from 2D Cranial X-Rays. Computer Graphics Forum. 2018;37(2):377-88.

13) Čavojska J, Petrasch J, Mattern D, et al. Estimating and abstracting the 3D structure of feline bones using neural networks on X-ray (2D) images. Commun Biol 2020;3(1):337.

14) Girdhar R, Fouhey DF, Rodriguez M, et al. Learning a predictable and generative vector representation for objects. European Conference on Computer Vision (ECCV) 2016;9910:484-99.

15) 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 2021;11(1):15249.

16) Goodfellow IJ, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. Adv Neur In 2014;27.

17) Isola P, Zhu JY, Zhou TH, Efros AA. Image-to-image translation with conditional adversarial networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017;5967-76.

18) Otake Y, Armand M, Armiger RS, et al. Intraoperative image-based multiview 2D/3D registration for image-guided orthopaedic surgery:incorporation of fiducial-based C-arm tracking and GPU-acceleration. IEEE Trans Med Imaging 2012;31(4):948-62.

19) Otake Y, Wang AS, Uneri A, et al. 3D-2D registration in mobile radiographs:algorithm development and preliminary clinical evaluation. Phys Med Biol 2015;60(5):2075-90.