DeepLap: A Deep Learning based Non-Specific Low Back Pain Symptomatic Muscles Recognition System

As sedentary and inactivity lifestyles are becoming increasingly common among humans, non-specific low back pain (nLBP) has gradually become an epidemic. It is necessary to recognize and locate symptomatic muscles which can be used to personalize the treatment. However, the existing symptomatic muscles recognition methods highly depend on physicians experience and lack objective criterions. And most of the diagnostic methods using biomedical signal, such as surface electromyography (sEMG), can only distinguish patients from normal people. EasiSMR is the only work that can recognize symptomatic muscles, but it suffers from low accuracy problem because it uses the handcrafted features. In this paper, we propose DeepLap, a deep learning based non-specific low back pain symptomatic muscles recognition system. It first extracts time and frequency domain sEMG from the raw sEMG signal. Then a heterogeneous two-stream multi-task deep learning algorithm is deployed, which processes the two inputs separately according to their characteristics. Moreover, we design a multitask neural network and propose Spanning CNN to take the muscles compensation information into account and improve the recognition accuracy. Finally, we design and implement a waist-belt-shaped wireless sEMG sensing and analysis system to validate the performance of our system. The system runs for 28 months on 288 participants in Xiyuan Hospital. Results show that DeepLap achieves an average accuracy of 92.9% in recognizing symptomatic nLBP low back muscles.

[1]  Trevor Darrell,et al.  Long-term recurrent convolutional networks for visual recognition and description , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  S. Giszter,et al.  Trunk Postural Muscle Timing Is Not Compromised In Low Back Pain Patients Clinically Diagnosed With Movement Coordination Impairments. , 2017, Motor control.

[3]  Tara L. Diesbourg,et al.  The effect of rest break schedule on acute low back pain development in pain and non-pain developers during seated work. , 2016, Applied ergonomics.

[4]  T. Seyed Hoseinpoor,et al.  EMG Activity of Trunk Muscles in Patients with Chronic Low Back Pain after Fatigue , 2014 .

[5]  J. Cabri,et al.  Recurrence quantification analysis and support vector machines for golf handicap and low back pain EMG classification. , 2015, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[6]  Lei Wang,et al.  Recognition of Chronic Low Back Pain During Lumbar Spine Movements Based on Surface Electromyography Signals , 2018, IEEE Access.

[7]  Dario Farina,et al.  Multiday EMG-Based Classification of Hand Motions with Deep Learning Techniques , 2018, Sensors.

[8]  Clément Gosselin,et al.  Transfer learning for sEMG hand gestures recognition using convolutional neural networks , 2017, 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[9]  Mark Laslett,et al.  Clinical classification in low back pain: best-evidence diagnostic rules based on systematic reviews , 2017, BMC Musculoskeletal Disorders.

[10]  Martin Underwood,et al.  Non-specific low back pain , 2012, The Lancet.

[11]  Bo-ram Choi,et al.  Differences between two subgroups of low back pain patients in lumbopelvic rotation and symmetry in the erector spinae and hamstring muscles during trunk flexion when standing. , 2013, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[12]  C. France,et al.  Sørensen test performance is driven by different physiological and psychological variables in participants with and without recurrent low back pain. , 2019, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[13]  Andrew Zisserman,et al.  Two-Stream Convolutional Networks for Action Recognition in Videos , 2014, NIPS.

[14]  F. C. T. Helm,et al.  Improved identification of dystonic cervical muscles via abnormal muscle activity during isometric contractions , 2015, Journal of the Neurological Sciences.

[15]  Jürgen Schmidhuber,et al.  Deep Neural Network Frontend for Continuous EMG-Based Speech Recognition , 2016, INTERSPEECH.

[16]  Catherine Disselhorst-Klug,et al.  The relationship between functionality and erector spinae activity in patients with specific low back pain during dynamic and static movements. , 2018, Gait & posture.

[17]  Nicolai Marquardt,et al.  Pain level recognition using kinematics and muscle activity for physical rehabilitation in chronic pain , 2015, 2015 International Conference on Affective Computing and Intelligent Interaction (ACII).

[18]  Lu Wang,et al.  FLoc: Device-free passive indoor localization in complex environments , 2017, 2017 IEEE International Conference on Communications (ICC).

[19]  Daniel Massicotte,et al.  Naive Bayesian learning for small training samples: Application on chronic Low Back Pain diagnostic with sEMG sensors , 2015, 2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings.

[20]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  F. Hug,et al.  Insight into motor adaptation to pain from between-leg compensation , 2014, European Journal of Applied Physiology.

[22]  Martial Hebert,et al.  Cross-Stitch Networks for Multi-task Learning , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Yinghong Peng,et al.  EMG‐Based Estimation of Limb Movement Using Deep Learning With Recurrent Convolutional Neural Networks , 2018, Artificial organs.

[24]  A. Guével,et al.  Motor adaptations to local muscle pain during a bilateral cyclic task , 2016, Experimental Brain Research.

[25]  Jing Xiao,et al.  EasiSMR: Recognizing Non-Specific Low Back Pain Symptomatic Muscles Using Multi-Muscles Fusion based Machine Learning , 2018, 2018 IEEE 4th International Conference on Computer and Communications (ICCC).

[26]  F. Jesus-Moraleida,et al.  Association between Physical Activity and Disability in patients with low back pain , 2017 .

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

[28]  Mohan S. Kankanhalli,et al.  A multi-stream convolutional neural network for sEMG-based gesture recognition in muscle-computer interface , 2017, Pattern Recognit. Lett..

[29]  Clément Gosselin,et al.  A convolutional neural network for robotic arm guidance using sEMG based frequency-features , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[30]  H. Hermens,et al.  SENIAM 8: European recommendations for surface electromyography , 1999 .

[31]  R. Salehi,et al.  Comparison of muscle recruitment patterns during sit to stand and stand to sit in “movement system impairment” subgroups of low back pain and healthy women , 2018 .