Intelligent analysis of coronal alignment in lower limbs based on radiographic image with convolutional neural network

One of the first tasks in osteotomy and arthroplasty is to identify the lower limb varus and valgus deformity status. The measurement of a set of angles to determine this status is generally performed manually with the measurement accuracy depending heavily on the experience of the person performing the measurements. This study proposes a method for calculating the required angles in lower limb radiographic (X-ray) images supported by the convolutional neural network. To achieved high accuracy in the measuring process, not only is a decentralized deep learning algorithm, including two orders for the radiographic, utilized, but also a training dataset is built based on the geometric knowledge related to the deformity correction principles. The developed algorithm performance is compared with standard references consisting of manually measured values provided by doctors in 80 radiographic images exhibiting an impressively low deviation of less than 1.5° in 82.3% of the cases.

[1]  R. Scott,et al.  The correction of severe varus deformity in total knee arthroplasty by tibial component downsizing and resection of uncapped proximal medial bone. , 2004, The Journal of arthroplasty.

[2]  Qianjin Feng,et al.  Cascade of multi-scale convolutional neural networks for bone suppression of chest radiographs in gradient domain , 2017, Medical Image Anal..

[3]  M. Ritter,et al.  Total knee arthroplasty in patients with angular varus or valgus deformities of > or = 20 degrees. , 2004, The Journal of arthroplasty.

[4]  Konstantinos Kamnitsas,et al.  Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation , 2016, Medical Image Anal..

[5]  Tiezheng Sun,et al.  Bony landmarks and rotational alignment in total knee arthroplasty for Chinese osteoarthritic knees with varus or valgus deformities. , 2009, The Journal of arthroplasty.

[6]  Xiaolin Hu,et al.  Recurrent convolutional neural network for object recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  S. Houterman,et al.  Femoral Mechanical–Anatomical Angle Measurements in Total Knee Arthroplasty: Analog versus Digital , 2014, The Journal of Knee Surgery.

[8]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[9]  L. Draganich,et al.  The effect of marginal osteophytes on reduction of varus-valgus instability in osteoarthritic knees. , 1990, Arthritis and rheumatism.

[10]  Simone Palazzo,et al.  Deep learning for automated skeletal bone age assessment in X‐ray images , 2017, Medical Image Anal..

[11]  R. Scott,et al.  Balancing severe valgus deformity in total knee arthroplasty using a lateral cruciform retinacular release. , 2004, The Journal of arthroplasty.

[12]  H. Yamamoto,et al.  A new computer-assisted method for measuring the tibio-femoral angle in patients with osteoarthritis of the knee. , 2004, Osteoarthritis and cartilage.

[13]  P. Sarangi,et al.  Severe varus and valgus deformities treated by total knee arthroplasty. , 1994, The Journal of bone and joint surgery. British volume.

[14]  Christopher Joseph Pal,et al.  Brain tumor segmentation with Deep Neural Networks , 2015, Medical Image Anal..

[15]  Luca Maria Gambardella,et al.  Max-pooling convolutional neural networks for vision-based hand gesture recognition , 2011, 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).

[16]  P. Lobenhoffer,et al.  Digital planning of high tibial osteotomy. Interrater reliability by using two different software , 2012, Knee Surgery, Sports Traumatology, Arthroscopy.

[17]  D. Hungerford,et al.  The effect of extraarticular varus and valgus deformity on total knee arthroplasty. , 1991, Clinical orthopaedics and related research.

[18]  Dror Paley,et al.  Principles of Deformity Correction , 2003 .

[19]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[20]  Carmen C. Y. Poon,et al.  Automatic Detection and Classification of Colorectal Polyps by Transferring Low-Level CNN Features From Nonmedical Domain , 2017, IEEE Journal of Biomedical and Health Informatics.

[21]  Wadim Wojciechowski,et al.  Automated measurement of parameters related to the deformities of lower limbs based on x-rays images , 2016, Comput. Biol. Medicine.

[22]  André Gooßen,et al.  Model-based segmentation of pediatric and adult joints for orthopedic measurements in digital radiographs of the lower limbs , 2011, Computer Science - Research and Development.

[23]  Hamid Jafarkhani,et al.  A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI , 2015, Medical Image Anal..

[24]  Tara N. Sainath,et al.  Improving deep neural networks for LVCSR using rectified linear units and dropout , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[25]  C. Ranawat,et al.  Total knee arthroplasty for severe valgus deformity. , 2005, The Journal of bone and joint surgery. American volume.

[26]  R. Iorio,et al.  Medial Reconstruction During Total Knee Arthroplasty for Severe Valgus Deformity , 1998, Clinical orthopaedics and related research.

[27]  Shlomo Wientroub,et al.  Intra- and interobserver reliability analysis of digital radiographic measurements for pediatric orthopedic parameters using a novel PACS integrated computer software program , 2010, Journal of children's orthopaedics.

[28]  C. Chang,et al.  Differences between Sagittal Femoral Mechanical and Distal Reference Axes Should Be Considered in Navigated TKA , 2009, Clinical orthopaedics and related research.

[29]  J. Insall,et al.  High tibial osteotomy for osteoarthritis of the knee with valgus deformity. , 1973, The Journal of bone and joint surgery. American volume.

[30]  Dong Chul Lee,et al.  High Tibial Osteotomy , 2012, Knee surgery & related research.

[31]  C. Stamoulis,et al.  Distal femoral valgus deformity following plate fixation of pediatric femoral shaft fractures. , 2013, The Journal of bone and joint surgery. American volume.

[32]  Garrison W. Cottrell,et al.  Understanding Convolution for Semantic Segmentation , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[33]  Max A. Viergever,et al.  Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks , 2016, Medical Image Anal..