A Comparative Study of End-To-End Discriminative Deep Learning Models for Knee Joint Kinematic Time Series Classification

One of the main motivations for classifying knee kinematic signals, namely the variation during a locomotion gait cycle of the angles the knee makes with respect to the three-dimensional (3D) planes of flexion/extension, abduction/adduction, and internal/external rotation, is to assist diagnosis of knee pathologies. These signals are informative but high dimensional, and highly variable, which has posed difficulties that have been addressed by machine learning algorithms. The purpose of this study is to investigate classification of knee kinematic signals through the entire gait using deep neural networks. The signals are first pre-processed to identify representative patterns, which are then used for deep learning of discriminative classifiers. This paper describes an efficient means of distinguishing between knee osteoarthrisis patients and asymptomatic participants, and our methods and experiments which validate it.

[1]  Angkoon Phinyomark,et al.  Analysis of Big Data in Gait Biomechanics: Current Trends and Future Directions , 2017, Journal of Medical and Biological Engineering.

[2]  Marcin Korytkowski,et al.  Convolutional Neural Networks for Time Series Classification , 2017, ICAISC.

[3]  Nicola Hagemeister,et al.  In vivo reproducibility of a new non-invasive diagnostic tool for three-dimensional knee evaluation , 1999 .

[4]  Germain Forestier,et al.  Deep learning for time series classification: a review , 2018, Data Mining and Knowledge Discovery.

[5]  H. Mecheri,et al.  Automatic filtering techniques for three-dimensional kinematics data using 3D motion capture system , 2006, 2006 IEEE International Symposium on Industrial Electronics.

[6]  Yixin Chen,et al.  Multi-Scale Convolutional Neural Networks for Time Series Classification , 2016, ArXiv.

[7]  Amar Mitiche,et al.  Kinematic gait analysis of workers exposed to knee straining postures by Bayes decision rule , 2015, Artif. Intell. Res..

[8]  Leena Sharma,et al.  The influence of alignment on risk of knee osteoarthritis progression according to baseline stage of disease. , 2002, Arthritis and rheumatism.

[9]  T. Cooke,et al.  Frontal plane knee alignment: a call for standardized measurement. , 2007, The Journal of rheumatology.

[10]  Mariem Abid,et al.  Knee Joint Biomechanical Gait Data Classification for Knee Pathology Assessment: A Literature Review , 2019, Applied bionics and biomechanics.

[11]  Laurence Cheze,et al.  Gait knee kinematic alterations in medial osteoarthritis: three dimensional assessment , 2014, International Orthopaedics.

[12]  Amar Mitiche,et al.  An analysis of 3D knee kinematic data complexity in knee osteoarthritis and asymptomatic controls , 2018, PloS one.

[13]  E S Growney,et al.  Reproducibility of the kinematics and kinetics of the lower extremity during normal stair‐climbing , 1997, Journal of orthopaedic research : official publication of the Orthopaedic Research Society.

[14]  M. Sati,et al.  Improving in vivo knee kinematic measurements: application to prosthetic ligament analysis , 1996 .

[15]  Tim Oates,et al.  Time series classification from scratch with deep neural networks: A strong baseline , 2016, 2017 International Joint Conference on Neural Networks (IJCNN).

[16]  Nicola Hagemeister,et al.  Reliability of a method for analyzing three-dimensional knee kinematics during gait. , 2008, Gait & posture.

[17]  Youssef Ouakrim,et al.  Representative Knee Kinematic Patterns Identification Using Within-Subject Variability Analysis , 2019 .

[18]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[20]  Sébastien Lustig,et al.  The KneeKG system: a review of the literature , 2012, Knee Surgery, Sports Traumatology, Arthroscopy.

[21]  Rachid Aissaoui,et al.  New comprehensive methods for the biomechanical analysis of knee osteoarthritis , 2011 .

[22]  Amar Mitiche,et al.  Mechanical biomarkers of medial compartment knee osteoarthritis diagnosis and severity grading: Discovery phase. , 2017, Journal of biomechanics.

[23]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[24]  Samy Bengio,et al.  The Handbook of Brain Theory and Neural Networks , 2002 .

[25]  L. Sharma,et al.  The role of knee alignment in disease progression and functional decline in knee osteoarthritis. , 2001, JAMA.

[26]  Alexandros Karatzoglou,et al.  Towards a universal neural network encoder for time series , 2018, CCIA.

[27]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[28]  N. Hagemeister,et al.  A reproducible method for studying three-dimensional knee kinematics. , 2005, Journal of biomechanics.

[29]  M. Akai,et al.  Association between in vivo knee kinematics during gait and the severity of knee osteoarthritis. , 2012, The Knee.