Neuromuscular disease detection based on feature extraction from time–frequency images of <scp>EMG</scp> signals employing robust hyperbolic Stockwell transform

Samanta, Kaniska; Chatterjee, Soumya; Bose, Rohit

doi:10.1002/ima.22709

Cited by 7 publications

(5 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various features have been utilized as input for different ML algorithms, resulting in variable performance outcomes, 42,43 as can be seen in Table S1. 34,35,39,[42][43][44][45][46][47][48][49][50][51][52][53][54][55][56][57][58][59] The classification performance varied when distinguishing between normal and myopathic, normal and neuropathic, or myopathic and neuropathic conditions. For instance, TD and FD techniques with K-nearest neighbors as a classifier, can achieve 100% accuracy in a small dataset differentiating ALS from normal, but only 66% accuracy in differentiating myopathy from normal.…”

Section: Emg Signal Classificationmentioning

confidence: 99%

“…Other strategies to overcome the difficulties with raw data processing include novel methods of feature extraction developed to harvest specific key attributes from the data. These extraction techniques are typically classified into time (or temporal) domain (TD), frequency domain (FD), and time‐frequency domain (TFD) 33–35 . Figures 4 and 5 show a visual sample of features extracted from EMG signals from normal participants, amyotrophic lateral sclerosis (ALS), and myopathy patients.…”

Section: Ai In Edx Medicinementioning

confidence: 99%

“…Various features have been utilized as input for different ML algorithms, resulting in variable performance outcomes, 42,43 as can be seen in Table S1 34,35,39,42–59 . The classification performance varied when distinguishing between normal and myopathic, normal and neuropathic, or myopathic and neuropathic conditions.…”

Section: Ai In Edx Medicinementioning

confidence: 99%

See 2 more Smart Citations

The role of artificial intelligence in electrodiagnostic and neuromuscular medicine: Current state and future directions

Taha,

Morren

2023

Muscle and Nerve

View full text Add to dashboard Cite

The rapid advancements in artificial intelligence (AI), including machine learning (ML), and deep learning (DL) have ushered in a new era of technological breakthroughs in healthcare. These technologies are revolutionizing the way we utilize medical data, enabling improved disease classification, more precise diagnoses, better treatment selection, therapeutic monitoring, and highly accurate prognostication. Different ML and DL models have been used to distinguish between electromyography signals in normal individuals and those with amyotrophic lateral sclerosis and myopathy, with accuracy ranging from 67% to 99.5%. DL models have also been successfully applied in neuromuscular ultrasound, with the use of segmentation techniques achieving diagnostic accuracy of at least 90% for nerve entrapment disorders, and 87% for inflammatory myopathies. Other successful AI applications include prediction of treatment response, and prognostication including prediction of intensive care unit admissions for patients with myasthenia gravis. Despite these remarkable strides, significant knowledge, attitude, and practice gaps persist, including within the field of electrodiagnostic and neuromuscular medicine. In this narrative review, we highlight the fundamental principles of AI and draw parallels with the intricacies of human brain networks. Specifically, we explore the immense potential that AI holds for applications in electrodiagnostic studies, neuromuscular ultrasound, and other aspects of neuromuscular medicine. While there are exciting possibilities for the future, it is essential to acknowledge and understand the limitations of AI and take proactive steps to mitigate these challenges. This collective endeavor holds immense potential for the advancement of healthcare through the strategic and responsible integration of AI technologies.

show abstract

Section: Emg Signal Classificationmentioning

confidence: 99%

Section: Ai In Edx Medicinementioning

confidence: 99%

See 1 more Smart Citation

The role of artificial intelligence in electrodiagnostic and neuromuscular medicine: Current state and future directions

Taha,

Morren

2023

Muscle and Nerve

View full text Add to dashboard Cite

show abstract

“…The parameters γf, γb and λ in Equation ( 2) are determined based on a population optimization method, as described in references [27,28] For the feature matrix obtained through the generalized S-transform, the following features are extracted: H1: Sum of column standard deviations, H2: Sum of row standard deviations, H3: Maximum value, H4: Sum of column variances, H5: Sum of variances along the main diagonal, H6: Sum of column kurtosis, and H7: Sum of row skewness. These 7 features can be used to compare the frequency, energy distribution, and spectral morphology of different datasets [29].…”

Section: Global Feature Extractionmentioning

confidence: 99%

Research on Circuit Breaker Operating Mechanism Fault Diagnosis Method Combining Global-Local Feature Extraction and KELM

Liu,

Wang,

Guo

et al. 2023

Sensors

View full text Add to dashboard Cite

In response to the lack of generality in feature extraction using modal decomposition methods and the susceptibility of diagnostic performance to parameter selection in traditional mechanical fault diagnosis of high-voltage circuit breaker operating mechanisms, this paper proposes a Global-Local feature extraction method based on Generalized S-Transform (S-Translate) combined with Gray Level Co-Occurrence Matrix (GLCM) and complemented by Maximum Relevance and Minimum Redundancy (mRMR) feature selection. The GL (Global-Local)-mRMR-KELM fault diagnosis model is proposed, which employs the Kernel Extreme Learning Machine (KELM). In this model, the original time-frequency domain features and the time-frequency features of the Generalized S-Transform matrix of vibration signals under different states of the circuit breaker are first extracted as global features. Then, the GLCM is obtained to extract texture features as local features. Finally, the mRMR and KELM are comprehensively applied to perform feature selection and classification on the dataset, thereby accomplishing the fault diagnosis of the circuit breaker’s operating mechanism. In this study, the 72.5 kV SF6 circuit breaker operating mechanism is taken as the research object, and three types of mechanical faults are simulated to obtain a vibration signal. Experimental results verify the effectiveness of the proposed GL-mRMR-KELM model, achieving a diagnostic accuracy of 96%. This research provides a feasible approach for the fault diagnosis of circuit breaker operating mechanisms.

show abstract

“…Muscle activities can be controlled by the signal transferred from the upper motor neurons in the brain to the lower motor neurons in the spinal cord [4]. Many researchers were concerned about the role of EMG in assessing muscle activity in ALS and myopathy (MYO), because ALS is commonly associated with muscle atrophy and significantly affects the neuron, causing serious damage to both the nervous and respiratory systems, whilst MYO begins to affect the skeletal fiber muscle, leading to inflammation [5][6][7]. Finally, the information from the classification stage is presented as control commands [8].…”

Section: Introductionmentioning

confidence: 99%

Emg Signal Classification for Neuromuscular Disorders Diagnosis Using TQWT and Bagging

Abdel-Maboud,

Alfonse,

Salem

et al. 2023

IJICIS

View full text Add to dashboard Cite

Electromyography (EMG) is a technique used to assess and record the electrical activity produced by skeletal muscles. This information can be used to diagnose muscle disorders, such as myopathy and Amyotrophic Lateral Sclerosis (ALS). In this study, we made a significant contribution to the field by proposing an automated method for classifying EMG signals that is more accurate than previous methods. Our method uses tunable-Q factor wavelet transform (TQWT) to decompose the EMG signal into its constituent components. These components are then used to calculate seven features that characterize the signal which are Interquartile Range (IQR), Mean Absolute Value (MAV), Mode, Kurtosis, Standard Deviation, Ratio of the absolute mean value , and Skewness. The features are then used to train a Bagging ensemble classifier. We evaluated our method on a dataset of EMG signals from healthy people, patients with myopathy, and patients with ALS. Our method achieved an accuracy of 99% in classifying the EMG signals. Our results suggest that the proposed method is a promising approach for diagnosing muscle disorders using EMG. This method could be used to improve the early diagnosis and treatment of these disorders.

show abstract

Neuromuscular disease detection based on feature extraction from time–frequency images of EMG signals employing robust hyperbolic Stockwell transform

Cited by 7 publications

References 40 publications

The role of artificial intelligence in electrodiagnostic and neuromuscular medicine: Current state and future directions

The role of artificial intelligence in electrodiagnostic and neuromuscular medicine: Current state and future directions

Research on Circuit Breaker Operating Mechanism Fault Diagnosis Method Combining Global-Local Feature Extraction and KELM

Emg Signal Classification for Neuromuscular Disorders Diagnosis Using TQWT and Bagging

Contact Info

Product

Resources

About