Aboofazeli, Mohammad

This paper presents an automated and objective method for extraction of swallowing sounds in a record of the tracheal breath and swallowing sounds. The proposed method takes advantage of the fact that swallowing sounds have more non-stationarity comparing with breath sounds and have large components in many wavelet scales whereas wavelet transform coefficients of breath sounds in higher wavelet scales are small. Therefore, a wavelet transform based filter was utilized in which a multiresolution decomposition-reconstruction process filters the signal. Swallowing sounds are detected in the filtered signal. The proposed method was applied to the tracheal sound recordings of 15 healthy and 11 dysphagic subjects. The results were validated manually by visual inspection using airflow measurement and spectrogram of the sounds and auditory means. Experimental results prove that the proposed method is more accurate, efficient, and objective than the methods proposed previously. Swallowing sound detection may be employed in a system for automated swallowing assessment and diagnosis of swallowing disorders (dysphagia) by acoustical means.

Nonlinear dynamics theory has been a tool of choice in the analysis of physiological signals and systems. This paper presents a novel approach in the analysis of tracheal swallowing and breath sounds based on nonlinear dynamics theory. As the tracheal sound signal is nonstationary, the signal was studied based on the recurrence quantification analysis (RQA) method, which is a useful technique in the analysis of nonstationary and noisy signals. Tracheal sound recordings of 15 healthy and 9 dysphagic subjects were studied. The multidimensional state space trajectory of each signal was reconstructed using Taken’s method of delays. The reconstructed trajectories were analyzed by the RQA technique. The preliminary results suggested that some recurrence parameters were appreciably different between swallowing and breath sounds. In order to confirm discriminating ability of the parameters, an automated method for extraction of swallowing sounds in the records of the tracheal swallowing and breath sounds was investigated. The swallowing sound extraction results were validated by manual inspection of the simultaneously recorded airflow signal and spectrogram of the sounds and also by auditory means. Experimental results proved that the investigated method more accurately detected the boundaries of swallowing sounds than methods proposed previously. Swallowing sound detection may be employed in a system for automated swallowing assessment and diagnosis of swallowing disorders (dysphagia) by acoustical means.

In recent years, acoustical analysis of the swallowing mechanism has received considerable attention due to its diagnostic potentials. This paper presents a hidden Markov model (HMM) based method for the swallowing sound segmentation and classification. Swallowing sound signals of 15 healthy and 11 dysphagic subjects were studied. The signals were divided into sequences of 25 ms segments each of which were represented by seven features. The sequences of features were modeled by HMMs. Trained HMMs were used for segmentation of the swallowing sounds into three distinct phases, i.e., initial quiet period, initial discrete sounds (IDS) and bolus transit sounds (BTS). Among the seven features, accuracy of segmentation by the HMM based on multi-scale product of wavelet coefficients was higher than that of the other HMMs and the linear prediction coefficient (LPC)-based HMM showed the weakest performance. In addition, HMMs were used for classification of the swallowing sounds of healthy subjects and dysphagic patients. Classification accuracy of different HMM configurations was investigated. When we increased the number of states of the HMMs from 4 to 8, the classification error gradually decreased. In most cases, classification error for N = 9 was higher than that of N = 8. Among the seven features used, root mean square (RMS) and waveform fractal dimension (WFD) showed the best performance in the HMM-based classification of swallowing sounds. When the sequences of the features of IDS segment were modeled separately, the accuracy reached up to 85.5%. As a second stage classification, a screening algorithm was used which correctly classified all the subjects but one healthy subject when RMS was used as characteristic feature of the swallowing sounds and the number of states was set to N = 8.

Automated detection of swallowing sounds in swallowing and breath sound recordings is of importance for monitoring purposes in which the recording durations are long. This paper presents a novel method for swallowing sound detection using hidden Markov modeling of recurrence plot features. Tracheal sound recordings of 15 healthy and nine dysphagic subjects were studied. The multidimensional state space trajectory of each signal was reconstructed using the Taken method of delays. The sequences of three recurrence plot features of the reconstructed trajectories (which have shown discriminating capability between swallowing and breath sounds) were modeled by three hidden Markov models. The Viterbi algorithm was used for swallowing sound detection. The results were validated manually by inspection of the simultaneously recorded airflow signal and spectrogram of the sounds, and also by auditory means. The experimental results suggested that the performance of the proposed method using hidden Markov modeling of recurrence plot features was superior to the previous swallowing sound detection methods.

Swallowing function is a complicated process involving several highly coordinated events. In recent years, acoustical analysis of the swallowing mechanism has received considerable attention due to its diagnostic potentials. This thesis presents novel approaches for analysis and modeling of swallowing sounds in individuals with and without swallowing disorder (dysphagia). Different techniques based on nonlinear dynamics, recuffence quantification analysis, hidden Markov model (HMM), and multiresolution wavelet analysis were used to detect characteristic features of swallowing sounds for automatic swallowing sound detection, swallowing sound segmentation, as well as classification of normal and dysphagic swallowing sounds. Data from 27 healthy subjects and 11 dysphagic patients were used, in which swallowing and breath sounds were recorded with an accelerometer placed over the trachea (suprasternal notch), while the subjects were fed three different textures with a bolus size of 5 ml. Submental electromyogram signals were also recorded in 12 normal subjects simultaneously with their swallowing sounds. In terms of swallowing sound detection in the swallow and breath sound recordings, the performance of the HMM based method using recurrence plot features was superior to that of the other methods. As for the segmentation of the swallowing sounds, multiscale products of wavelet coefficients along with an HMM yielded the least error in detecting the boundaries between the segments. Lastly, in terms of classification of normal and dysphagic swallowing sounds, nonlinear metric tools, i.e., correlation dimension and time delay, resulted in a high accuracy of 837o. The results of HMM based methods for classification of swallowing sounds between the two groups of healthy and dysphagic subjects using RMS achieved 85.5Vo accuracy. The results of the study on the timing of submental muscle contraction in relation to swallowing sounds showed that the movement of the larynx precedes the fust audible segment of swallowing sounds. It also showed that the lag between the onset of submental muscle contraction and the beginning of initial discrete sounds is shorter for thin liquid texture. Overall, the outcomes of this study have paved the way for a better understanding of the swallowing mechanism and improving clinical assessment techniques of swallowing disorders using its acoustic signatures.