image: This graphic illustrates the potential for collecting and processing iEMG signals for diagnostic purposes using the proposed algorithm. The intramuscular signals from a person's right upper arm are recorded (shown as the pink spot). The adjacent circle shows the details of the needle electrode and the signal recording setup. The signal waveforms (on laptop screen) are then processed to extract the feature (1-D CSLBP) that effectively captures the differences underlying different neuromuscular disorders. The output of this processing step is supplied to the artificial neural network—machine learning approach—that performs the (binary) classification. The classification step is depicted by the graph with an inclined line bisecting the two classes, corresponding to the signals for myopathy (green dots) and neuropathy (orange dots), respectively. The respective colored arrows point to the muscle fiber cross-section corresponding to myopathy (green) and neuropathy (orange). For aesthetic appeal, the dark background has a transparent overlay of neurons (light brown) to convey the context of the underlying cause of neuromuscular disorders. view more
Credit: Created using biorender.com by V. Shenoy Handiru.
East Hanover, NJ. December 22, 2022. A team of researchers has developed a promising new approach to detecting neuromuscular disorders using intramuscular electromyography (iEMG). In a pilot study, the automatic diagnostic system showed high accuracy in three muscle types and low computational time. Their article, "Intramuscular EMG classifier for detecting myopathy and neuropathy" (doi: 10.1002/ima.22811), was published online on October 18, 2022, by the International Journal of Imaging Systems Technology. It is available at: https://onlinelibrary.wiley.com/doi/abs/10.1002/ima.22811
The authors are Shobha Jose, Thomas George Selveraj, Jobin T. Philip, Sairamya Nanjappan Jothiraj, and Subathra Muthu Swamy Pandian from Karunya Institute of Technology and Sciences in Tamil Nadu, India, Kenneth Samuel of Eastern University in St. David’s, Pennsylvania, and Vikram Shenoy Handiru, and Easter S. Suviseshamuthu, from the Center for Mobility and Rehabilitation Engineering Research at Kessler Foundation in West Orange, New Jersey.
Invasive intramuscular EMG has been shown to be an effective tool for identifying neuromuscular abnormalities such as myopathy and neuropathy. Myopathy, a disorder of muscle fibers, and neuropathy, which reflects damage to peripheral nerves, exhibit different patterns of motor unit action potentials. To facilitate the interpretation of these signals, the team developed an iEMG classifier framework based on a new feature called 1-Dimensional Center Symmetric Local Binary Pattern (I-D, CSLBP), which enhanced the performance of a binary (myopathy and neuropathy) classification task.
The electromyographic signals from the biceps brachii, deltoideus, and vastus medialis muscles. Some of 25 individuals were studied: 10 healthy controls, 7 with myopathy, and 8 with neuropathy. Classification accuracy for the three muscle types exceeded 92 percent, and computational time was low.
“This high level of accuracy combined with a short time frame for testing indicates the potential for real-time implementation,” stated Dr. Suviseshamuthu. “Future research is needed to test the feasibility of a real-time EMG system that would aid clinicians in making quick, objective, and accurate diagnoses of these neuromuscular disorders,” he added.
Relevant Resources:
Jose S, George, ST, Subathra, MSP, Handiru VS, Jeevanandam PK, Amato U, Suviseshamuthu ES. Robust classification of intramuscular EMG signals to aid the diagnosis of neuromuscular disorders. IEEE Open J Eng Med Biol. 2020 Aug 17; 1:235-242 doi: 10.1109/OJEMB.2020.3017130. eCollection 2020.
Suviseshamuthu ES, Shenoy Handiru V, et al. EEG-based spectral analysis showing brainwave changes related to modulating progressive fatigue during a prolonged intermittent motor task. Front Hum Neurosci, 11 March 2022, https://doi.org/10.3389/fnhum.2022.770053.
About Kessler Foundation
Kessler Foundation, a major nonprofit organization in the field of disability, is a global leader in rehabilitation research that seeks to improve cognition, mobility, and long-term outcomes, including employment, for people with neurological disabilities caused by diseases and injuries of the brain and spinal cord. Kessler Foundation leads the nation in funding innovative programs that expand opportunities for employment for people with disabilities. For more information, visit KesslerFoundation.org.
For more information, or to interview an expert, contact: Carolann Murphy, CMurphy@KesslerFoundation.org.
Tweet: New application of intramuscular #EMG may facilitate detection of #neuromuscular disorders #myopathy #neuropathy #Kesslerfoundation @karunyauniv #bioengineering #RehabResearch
Graphics:
Title: Schematic of the collection and processing of intramuscular EMG signals
Caption: This graphic illustrates the potential for collecting and processing iEMG signals for diagnostic purposes using the proposed algorithm.
Alt-text: The intramuscular signals from a person's right upper arm are recorded (shown as the pink spot). The adjacent circle shows the details of the needle electrode and the signal recording setup. The signal waveforms (on laptop screen) are then processed to extract the feature (1-D CSLBP) that effectively captures the differences underlying different neuromuscular disorders. The output of this processing step is supplied to the artificial neural network—machine learning approach—that performs the (binary) classification. The classification step is depicted by the graph with an inclined line bisecting the two classes, corresponding to the signals for myopathy (green dots) and neuropathy (orange dots), respectively. The respective colored arrows point to the muscle fiber cross-section corresponding to myopathy (green) and neuropathy (orange). For aesthetic appeal, the dark background has a transparent overlay of neurons (light brown) to convey the context of the underlying cause of neuromuscular disorders.
Created using bioorender.com by V. Shenoy Handiru.
Title: Vikram Shenoy Handiru, PhD
Caption: Dr. Shenoy Handiru is a research scientist in the Center for Mobility and Rehabilitation Engineering Research at Kessler Foundation.
Title: Easter S. Suviseshamuthu, PhD
Caption: Dr. Suviseshamuthu is a research scientist in the Center for Mobility and Rehabilitation Engineering Research at Kessler Foundation.
Journal
International Journal of Imaging Systems and Technology
Method of Research
Computational simulation/modeling
Subject of Research
People
Article Title
Intramuscular EMG classifier for detecting myopathy and neuropathy
Article Publication Date
18-Oct-2022