Traditionally, the clinical diagnosis of a respiratory disease is made from a careful clinical examination including chest auscultation. Objective analysis and automatic interpretation of the lung sound based on its physical characters are strongly warranted to assist clinical practice. In this paper, a new method is proposed to distinguish between the normal and the abnormal subjects using the morphological complexities of the lung sound signals. The morphological embedded complexities used in these experiments have been calculated in terms of texture information (lacunarity), irregularity index (sample entropy), third order moment (skewness), and fourth order moment (Kurtosis). These features are extracted from a mixed data set of 10 normal and 20 abnormal subjects and are analyzed using two different classifiers: extreme learning machine (ELM) and support vector machine (SVM) network. The results are obtained using 5-fold cross-validation. The performance of the proposed method is compared with a wavelet analysis based method. The developed algorithm gives a better accuracy of 92.86% and sensitivity of 86.30% and specificity of 86.90% for a composite feature vector of four morphological indices.
The audio information of respiratory signals is used to find out the pulmonary dysfunctions. The diagnostic status of the respiratory system can be assessed by interpreting the audible characteristics of lung sound signals in terms of varying amplitude, intensity, and tone quality or modal frequencies. Physicians examine the lung disease in two ways: one is noninvasive process which includes auscultation, pulmonary function test, respiratory inductance plethysmograph, and phonopneumography technique and the other is invasive approach such as chest X-ray or roentgenogram and computerized tomography (CT) scan, and so forth. The invasive diagnostic procedures are expensive, time consuming, and harmful as in case of X-ray repetition. One of the popular noninvasive approaches is auscultation, a stethoscope device based technique, started after the invention of stethoscope by French physician Laennec in 1962 [
The nonlinear and nonstationary properties of lung sound signal make it difficult to diagnose the lungs status using only the temporal or spectral characteristics of the respiratory sounds. The lung sound (LS) shows a complex dynamics because of the involvement of transmission path filtering effect, attenuation, and its production mechanism which is unstable. The pathological status of the lungs signifies a morphological deviation of the normal breath sound. The pattern complexities of abnormal LS are higher than that of the normal LS because of the occurrence of auxiliary signals in case of unhealthy lungs. The doctors take help of different clinical devices, namely, modern electronic stethoscope, CT scan, bronchoscopy, and so forth, to capture the various distinctive parameters of the normal as well as abnormal states of the lungs. The accuracy of diagnosis with these diagnostic tools depends on the experience and knowledge of the physicians and also on the cooperation of the patients.
With the advances of computer technologies, statistical signal processing, artificial intelligence, and pattern recognition algorithms, lung sound analysis is commenced in an automated manner. The computer aided or microprocessor based automated tools offer several facilities in terms of high speed, large storage capacity and avoid the manual hazards. The important intervening step of automated lung sound analysis is the extraction of authentic features that are inherently correlated with the lungs conditions. The final stage of pattern recognition based lung sound analysis system is decision making about the underlying disease, if any. The aim of feature extraction procedure is to identify the relevant distinct parameters of the LS signals and to arrange them in vector form that serves as an input during classification. Researchers have developed several feature extraction techniques to form the feature vectors based on parametric and nonparametric methods. In parametric technique models the LS signal based on a priori knowledge is in contrast with nonparametric method which characterizes LS signal using a set of basis functions [
The first initiative for lung sounds analysis was taken by Forgacs et al. in the late 1960s [
Marshall and Boussakta [
The difficulties are faced by researchers in analysis of respiratory sounds that are the interference of lung sounds with heart sounds, appearance of different pathological sounds in similar forms, and also the unavailability of the sophisticated instrumentation for processing information embedded in the lung sounds. The focus of the study is to develop a new method for better analysis of lung sounds by exploring the statistical approaches and digital signal processing knowledge combined with pattern recognition algorithms. In this paper, a new technique is proposed to detect the lungs status, normal and abnormal, using the structural complexities of LS signals. The structural behavioral of the LS signal is parameterized with a number of distinct features such as sample entropy, lacunarity, skewness, and kurtosis. A twenty-four-dimensional feature vector is formed using these parameters. The ELM and SVM networks are used to evaluate the efficiency of the developed technique. The proposed technique gives better performance than the baseline method [
The rest of this paper is organized as follows. Theoretical background information on ELM and SVM classifiers is described in Section
In 2006, Huang et al. proposed a high speed and simple learning algorithm to remove the drawbacks of conventional learning algorithms for a single layer feed forward network (SLFN) [
Consider an activation function
Assign hidden layer biases
Compute the output matrix
Compute the output weights
However, the classification accuracy of the ELM network depends on the number of hidden nodes and the selection of the activation functions. In this work we have chosen radial basis activation function and an ELM network whose hidden layer consists of
Structure of ELM network.
The support vector machine (SVM) network was proposed by Cortes and Vapnik in 1995 as an alternative tool of multilayer feedforward neural network [
The decision surface of (
An optimal hyperplane can be obtained by minimizing the function
To construct a decision function
The kernel function
The recorded lung sounds are contaminated with environmental noise, manmade artifacts, data recording and processing instruments’ disturbances, and heart sound interference which leads to an incorrect detection of the lungs conditions. In this work, we have reduced the surrounding noise by recording the lung sounds in a quite environment and manmade artifacts are suppressed by placing the stethoscope in a proper way over the recording positions of the subjects. The instrumental disturbances are removed with a first order differentiation algorithm [
(a) It depicts the waveform of a noisy lung sound signal. (b) It shows the corresponding differentiation output of the nosy normal LS.
Graphical results of the EMD based HS removal technique (proposed by us). (a) It shows the waveform of a mixed LS signal (20% LS + 80% HS). (b) It shows the waveform of a mixed LS signal (50% LS + 50% HS). (c) It shows the waveform of a mixed LS signal (80% LS + 20% HS), (d) Reconstructed LS signal, (e) Residual HS signal.
It is seen that inspiration and expiration phase of a lung sound cycle carries significant information regarding the lungs conditions. Hence, one complete breathing cycle is required to diagnose the lungs’ status using morphological complexities of the respiratory sound signals. In this study, we calculate one complete respiratory cycle using a new algorithm developed by us based on Hilbert transform (HT) [
Calculate envelope
Smoothing of envelope signal
The transition points
The duration of inspiration or expiration phase is calculated by measuring the distance between two consecutive minima points
(1) (2) (3) (4) (5)
(a) depicts the waveform of a normal LS signal. (b) It shows the Hilbert envelope and (c) shows the smoothen envelope. (d) First order derivative of the smoothen envelope curve. (e) The red line defined a respiratory cycle estimated by the distance between two consecutive phases.
One of the most important steps in respiratory sounds analysis is to identify the relevant inherent properties of the lung sound signals. These attributes are useful for modeling the healthy and unhealthy conditions of the lungs. The respiratory sounds are complex in nature because of the randomized vibration of the air ways walls and turbulent flow of gases through the respiratory system. The dynamical complexities of the abnormal lung sound are higher than that of the normal lung sound because of the presence of auxiliary sound in abnormal cases. Hence, morphological patterns of the abnormal lung sounds deviate from that of the normal sounds in a certain degree of alignment. The temporal domain features are not relevant in diagnosing of respiratory diseases because of the equivalent resemble for the both cases of normal and abnormal patients. On the other hand, the spectral domain characteristics of the lung sounds do not meet the requirements of pattern recognition due to the nonstationary behavior of the signals. The respiratory signals show non-stationarity characteristic because of the change in lung volume during the breathing process [
(a) and (c) display the normal and abnormal lung sound waveforms. (b) and (d) show the probability distribution functions for normal and abnormal cases.
In this paper, four types of features
Computation of kurtosis (
Estimation of skewness (
Calculation of lacunarity (
Computate the box mass
Repeate Step
Calculate the probability distribution
Estimate of the first
Calculate the lacunarity value for the size
Computation of sample entropy (
The templates or vectors of size
The distance
Counting the number of templates matching for a given template
The conditional probability of template matching for a signal having
The sample entropy values are calculated by
The lung sound signals are recorded from the abnormal as well as normal male and female subjects with different types of pulmonary dysfunctions: Chronic Obstructive Pulmonary Diseases (COPDs), Interstitial Lung Diseases (ILDs) and asthma. These recordings are collected from various resources: Audio & Biosignal Processing laboratory, IIT Kharagpur and Institute of Pulmocare and Research, Kolkata, India. A total of
The whole analysis is implemented on an ACER-PC with 3.29 GHz Intel core 2 quad CPU and 3.49 GB of RAM. The MATLAB (R2008a, The Mathworks, Inc., Natick, MA) tool is used for conducting all the experiments.
The lung sounds data employed in this experiment are reported in Section
The experimental results are shown in Tables
Performance of ELM and SVM classifier for different sets of the proposed feature vectors.
Type of classifier | Feature set | Feature vector | SEN (%) | SPE (%) | CA (%) | Training time (ms) | Testing time (ms) |
---|---|---|---|---|---|---|---|
ELM | Set-1 |
|
|
|
|
|
0.57 |
SVM | Set-1 |
|
|
|
|
|
2.10 |
ELM | Set-2 |
|
|
|
|
|
0.65 |
SVM | Set-2 |
|
|
|
|
|
5.70 |
ELM | Set-3 |
|
|
|
|
|
3.70 |
SVM | Set-3 |
|
|
|
|
|
8.10 |
Comparison of performances between the proposed and baseline methods [
Method | Feature vector | Type of |
SEN (%) | SPE (%) | CA (%) | Training time (ms) | Testing time (ms) |
---|---|---|---|---|---|---|---|
Proposed |
|
ELM |
|
|
|
|
3.70 |
Method |
|
SVM |
|
|
|
|
|
Baseline |
|
ELM |
|
|
|
|
|
Method [ |
|
SVM |
|
|
|
|
|
SEN: sensitivity; SPE: specificity; CA: classification accuracy;
This paper proposes a new method to detect the normal and abnormal conditions of the lungs in a non-invasive manner by exploring the inherent morphological characteristics of the lung sound signals using ELM network. The method is very fast because ELM network avoids the tuning of input weights and hidden layer biases by randomly selecting them during the learning process. The efficiency of the algorithm is tested for three combined feature vector sets. The proposed method gives a better accuracy of
The authors declare that there is no conflict of interests regarding the publication of this paper.