An automatic markerless knee tracking and registration algorithm has been proposed in the literature to avoid the marker insertion required by conventional computer-assisted knee surgery, resulting in a shorter and less invasive surgical workflow. However, such an algorithm considers intact femur geometry only. The bone surface modification is inevitable due to intra-operative intervention. The mismatched correspondences will degrade the reliability of registered target pose. To solve this problem, this work proposed a supervised deep neural network to automatically restore the surface of processed bone. The network was trained on a synthetic dataset that consists of real depth captures of a model leg and simulated realistic femur cutting. According to the evaluation on both synthetic data and real-time captures, the registration quality can be effectively improved by surface reconstruction. The improvement in tracking accuracy is only evident over test data, indicating the need for future enhancement of the dataset and network.
Xue Hu
,
Ferdinando Rodriguez y Baena
. Automatic Bone Surface Restoration for Markerless Computer-Assisted Orthopaedic Surgery[J]. Chinese Journal of Mechanical Engineering, 2022
, 35(1)
: 18
-18
.
DOI: 10.1186/s10033-022-00684-6
An automatic markerless knee tracking and registration algorithm has been proposed in the literature to avoid the marker insertion required by conventional computer-assisted knee surgery, resulting in a shorter and less invasive surgical workflow. However, such an algorithm considers intact femur geometry only. The bone surface modification is inevitable due to intra-operative intervention. The mismatched correspondences will degrade the reliability of registered target pose. To solve this problem, this work proposed a supervised deep neural network to automatically restore the surface of processed bone. The network was trained on a synthetic dataset that consists of real depth captures of a model leg and simulated realistic femur cutting. According to the evaluation on both synthetic data and real-time captures, the registration quality can be effectively improved by surface reconstruction. The improvement in tracking accuracy is only evident over test data, indicating the need for future enhancement of the dataset and network.
[1] D C Flanigan, J D Harris, T Q Trinh, et al. Prevalence of chondral defects in athletes' knees:a systematic review. Medicine & Science in Sports & Exercise, 2010, 42(10):1795-1801.
[2] F Tatti, H Iqbal, B Jaramaz, et al. A novel computer-assisted workflow for treatment of osteochondral lesions in the knee. The 20th Annual Meeting of the International Society for Computer Assisted Orthopaedic Surgery, 2020(4):250-253.
[3] D K Bae, S J Song. Computer assisted navigation in knee arthroplasty. Clinics in Orthopedic Surgery, ?2011, 3(4):259-267.
[4] D C Beringer, J J Patel, K J Bozic. An overview of economic issues in computer-assisted total joint arthroplasty. Clinical Orthopaedics and Related Research ®, 2007, 463:26-30.
[5] A D Pearle, P F O'Loughlin, D O Kendoff. Robot-assisted unicompartmental knee arthroplasty. The Journal of Arthroplasty, ?2010, 25(2):230-237.
[6] R W Wysocki, M B Sheinkop, W W Virkus, et al. Femoral fracture through a previous pin site after computer-assisted total knee arthroplasty. The Journal of Arthroplasty, 2008, 23(3):462-465.
[7] A P Schulz, K Seide, C Queitsch, et al. Results of total hip replacement using the robodoc surgical assistant system:clinical outcome and evaluation of complications for 97 procedures. The International Journal of Medical Robotics and Computer Assisted Surgery, 2007, 3(4):301-306.
[8] H Liu, F R Y Baena. Automatic markerless registration and tracking of the bone for computer-assisted orthopaedic surgery. IEEE Access, 2020, 8:42010-42020.
[9] P Rodrigues, M Antunes, C Raposo, et al. Deep segmentation leverages geometric pose estimation in computer-aided total knee arthroplasty. Healthcare Technology Letters, 2019, 6(6):226-230.
[10] X Hu, A Nguyen, F R y Baena. Occlusion-robust visual markerless bone tracking for computer-assisted orthopaedic surgery. IEEE Transactions on Instrumentation and Measurement, 2021.. https://doi.org/10.1109/TIM.2021.3134764
[11] F M M da Cunha Cavalcanti, D Doca, M Cohen, et al. Updating on diagnosis and treatment of chondral lesion of the knee. Revista Brasileira de Ortopedia, 2012, 47(1):12-20.
[12] C R Wheeless. Chondral and osteochondral injuries of the knee. In:Wheeless' Textbook of Orthopaedics, 2001.
[13] A Kurenkov, J Ji, A Garg, et al. Deformnet:free-form deformation network for 3D shape reconstruction from a single image. 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2018:858-866.
[14] X Han, H Laga, M Bennamoun. Image-based 3D object reconstruction:state-of-the-art and trends in the deep learning era. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(5):1578-1604.
[15] M Tatarchenko, A Dosovitskiy, T Brox. Multi-view 3D models from single images with a convolutional network. European Conference on Computer Vision, 2016:322-337.
[16] J Wang, B Sun, Y Lu. Mvpnet:multi-view point regression networks for 3D object reconstruction from a single image. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33:8949-8956.
[17] D Eigen, C Puhrsch, R Fergus. Depth map prediction from a single image using a multi-scale deep network. Advances in Neural Information Processing Systems, 2014:2366-2374.
[18] C R Qi, H Su, K Mo, et al. Pointnet:deep learning on point sets for 3D classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017:652-660.
[19] Y Aoki, H Goforth, R A Srivatsan, et al. Pointnetlk:robust & efficient point cloud registration using pointnet. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019:7163-7172.
[20] L Keselman, J I Woodfill, A Grunnet-Jepsen, et al. Intel(r) realsense(tm) stereoscopic depth cameras. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017:1267-1276.
[21] S Choi, Q Y Zhou, V Koltun. Robust reconstruction of indoor scenes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015:5556-5565.
[22] Q Y Zhou, J Park, V Koltun. Open3D:a modern library for 3D data processing. 2018, arXiv:1801.09847.
