*5.2.2. MUP template / MUPT characterization*

A MUPT is composed of the MUPs created by a single MU. The typical MUP shape of a MUPT is represented by its MUP template. The stability of the MUPs with in a MUPT can be estimated as can the firing behavior of the MU that created the MUPT. MUPT characterization refers to performing supervised learning to determine if a MUPT was created by a normal or abnormal (disordered) MU, if just two categories are considered or by a myopathic, normal or neurogenic MU if three categories are considered. This characterization is based on a training stage that is performed using training data suitably representing each category. MUPT features used for MUPT characterization often consist of MUP template morphological features; features extracted from the time domain representation of the MUP template [4] as well as spectral features; those extracted from its frequency domain representation [4]. MU firing pattern features have not yet be effectively used. Typically, a feature selection step is performed to select the best feature subset. As is the case with any supervised learning problem, feature selection can be filter-based (quality metric of the feature subset depends on information content like interclass distance or correlation) or wrapper-based (quality metric of the feature subset depends on the accuracy of the characterization process using such feature set). However, wrapper-based feature selection techniques are used more frequently [56].

In addition to the intrinsic MUP template features, like turns, duration, amplitude, etc, combinations of features can be used if they improve the characterization results. For instance, MUP template thickness (area/amplitude) can be added to the features used for characteriza‐ tion to improve classification performance as the discriminative power of the feature set would be higher.

#### *5.2.2.1. Signal detection and preprocessing*

#### **1.** Level and/or window triggering

Individual MUPTs can be extracted for quantitative analysis using level or window triggering methods. These methods allow the MUPs created by a single MU to be extracted, but only if their amplitudes are unique with respect to the amplitudes of MUPs created by other MUs. These methods can be used with careful positioning of the needle and during low level of muscle activation. Only one MUPT can be extracted from the EMG signal detected during muscle contraction. Therefore, for each MUPT to be extracted a separate contraction must be performed.

*5.2.2.2. Non-transparent classification techniques*

and support vector machines.

made.

MUPT characterization can be performed using probabilistic techniques. Probabilistic techniques provide a MUP characterization in terms of conditional probabilities that sum to 1 across all of the categories considered. For instance, a probabilistic technique can suggest that considering the features of a MUPT there is a 10% probability it was detected in a myopathic muscle, a 70% probability it was detected in a normal muscle and a 20% probability it was

Clinical Quantitative Electromyography http://dx.doi.org/10.5772/56033 105

Various methods have been used in the literature to perform MUP template characterization, ranging from conventional to advanced classifiers. For example, linear discriminant analysis (LDA), decision trees and a standard Naive Bayes (NB) classifier were implemented and compared in [9]. LDA attempts to find a linear combination of features that maximizes the between class variance and minimizes the within class variance and it relies on this as a basis for optimal classification. Using these trivial classifiers has the advantage of being rather more transparent than using more advanced pattern recognition techniques like neural networks

Artificial neural networks were first used for MUP template characterization in [10] and [11]. More progress in this direction was achieved in [12] as artificial neural networks were used along with radial basis functions and probabilistic neural networks in a two-phase classifier, which increased MUPT characterization accuracy. In the second phase of the classification, a C4.5 decision tree was used to determine whether the disorder was myopathic or neurogenic, if any. Another example of using neural networks in MUP analysis can be found in [63].

In [53] autoregressive (AR) modeling and cepstral analysis were applied to characterize MUP templates and the training dataset was built on normal MUP templates as well as MUP templates taken from myopathic muscles. It was concluded in [53] that using AR modeling and cepstral analysis along with time domain features (in particular duration) led to catego‐ rizations with high accuracy in the assessment of myopathic MUP templates (in this work two categories were used; normal and myopathic). In [54], MUP templates were classified into three categories; normal, myopathic and neurogenic using support vector machines (SVM).

Using artificial neural networks in classification could lead to over-fitting; a classifier that has difficulty in producing the same accuracy with new or more generalized data. As mentioned earlier, using a SVM and artificial neural networks does not provide enough transparency and renders it more difficult for clinicians to understand how a certain classification decision was

An example of a transparent rule-based classification technique is the two-stage classifier developed in [55]. This two-stage classifier is based on utilizing radial basis function artificial neural networks and decision trees. The combined use of an artificial neural network and a decision tree reduces the number of tuned parameters required and allows an interpretation

*5.2.2.3. Transparent rule-based MUPT classification techniques*

of the classification decisions to be provided [55].

detected in a neurogenic muscle neurogenic if three categories are considered.

#### **2.** EMG signal decomposition

EMG signals are the linear summation of the MUPTs created by the MUs active in a muscle. EMG signal decomposition extracts individual MUPTs from an EMG signal. Unlike level or window triggering, EMG signal decomposition allows several MUPTs created by MUs concurrently active during a single muscle contraction to be analyzed. The accuracy of the MUPTs extracted by an EMG signal decomposition algorithm determines the type of analyses that can be successfully applied to the extracted MUPTs. The MUPTs extracted during EMG signal decomposition can be further analyzed to assist in diagnosing neuromuscular disorders.

EMG signal decomposition involves three main steps, described in the following paragraphs.

The first step is to detect the MUPTs comprising an EMG signal. Some EMG signal decompo‐ sition algorithms attempt to detect all the MUPTs that existed in the EMG signal while others attempt to extract only MUPTs that had a major contribution to the EMG signal. The following step is to determine the shapes of the different MUPs. This can be done by categorizing the MUPs in the signal based on their shapes and sizes. This categorization, if implemented properly, reveals clusters of MUPs with similar shapes and sizes. As a result, MUPs with different shapes and sizes should belong to different clusters. MUPs with similar shapes and sizes were most probably created by different discharges of the same MU, while MUPs with unique shapes and sizes (i.e. not belonging to cluster or to a cluster with very few members) are most probably superpositions. The main outcome of this step is to identify the number of MUs that contributed significant MUPs to the EMG signal (i.e. to estimate the number of MUPTs with significant MUPs) and to estimate the MUP template of each discovered MUPT.

The second step is to determine the class of every template. Superpositions of MUPs are harder to deal with in the first step as well as in this step. If the overlap is only slight, the constituents might still be recognizable. But if the overlap is complete it might be necessary to try different alignments of the templates to see which gives the closest fit. The motor unit discharge patterns can also be used to help determine which MUs are involved in a superimposed MUP [36]. As discharge rates are assumed to be rather orderly (i.e. IDIs can be assumed to follow a Gaussian distribution), the time at which a particular discharge took place can be estimated from the time at which the preceding or following discharge took place.

The final step in decomposition is to validate the results to ensure they are consistent with the expected physiological behavior of MUs. If there are unexpected short IDI in any of the discharge patterns, or if there are detected MUPs that have not been assigned to a MUPT, then the decomposition is probably not correct or incomplete. On the other hand, if all the activity in the signal (i.e. the detected MUPs) has been adequately accounted for by the set of extracted MUPTs which in turn represent MUs with physiologically realistic discharge patterns, then there is a good chance that the decomposition is substantially complete and accurate [36].
