Heart sound classification based on scaled spectrogram and partial least squares regression
Introduction
Many pathological conditions of the cardiovascular system are reflected in heart sound signals, which makes it possible to diagnose heart disease by analyzing heart sound signals. Heart sound auscultation is a method used to analyze heart sound signals using a stethoscope. Because of its easy implementation, auscultation is widely used in the clinical diagnosis of heart disease [1], [2]. However, the accuracy of auscultation depends on the skill and subjective experience of the physician [3]. Therefore, an objective analysis of heart sound signals is necessary. PCG signal analysis is another method of analyzing heart sound signals using phonocardiograms. The physiological and pathological information has been extracted from the PCG signal using signal processing and artificial intelligence techniques in the literature [3], [4]. With the PCG, the objective analysis of heart sound signals using computer technology is becoming popular. Moreover, telemedicine is becoming available with the development of electronic stethoscopes and smart phones [5]. Overall, the analysis of PCG signals has important significance for the diagnosis of heart disease. Heart sound classification aims at the automatic classification of PCG signals. It is very important for preliminary diagnosis.
Heart sound classification usually involves two steps. The first step is heart sound segmentation, which attempts to detect the location of the fundamental heart sounds (FHs). The FHs include the first (S1) and second (S2) heart sounds, which are the important physical characteristics of heart sounds. The accurate localization of the FHs shows the systolic and diastolic regions of the heart sounds. In addition, the heart cycles are identified by the FHs. Thus, the characteristics of different pathological situations in the region of one heart cycle are used to classify different heart sound categories. Many methods, such as the envelope-based method [6], the method using dynamic clustering [7] and the logistic regression-hsmm based method [8], have been developed for this task. However, heart sound segmentation remains a challenging task, and it is difficult to segment the FHs accurately in a noisy environment.
The second step of heart sound classification is to extract the features in one heart cycle and use the features for classification. Many features have been proposed in the literature. The three main types are time [5], frequency [9] and time-frequency complexity-based features [10], [11]. Although the time-frequency-based features are more computationally complex than features based on only time or frequency, they provide more comprehensive information about the PCG signal. Thus, time-frequency-based features usually outperform other features. The commonly used time-frequency feature extraction methods for PCG signals are wavelets [10], S-transform [12] and short time Fourier transform (STFT) [13]. The magnitude of the STFT yields the spectrogram. This spectrogram is used in this paper since it is easy to implement and convenient to scale.
The primary goal of heart sound classification is to identify different heart sound categories. This is not necessary for segmentation in some situations, especially when the heart cycles are known. So the estimation of heart cycle duration and alignment methods based on the envelope are proposed to obtain the heart cycles instead of locating both S1 and S2. The calculation process is simplified in this way. Although the correct segmentation information can improve the classification performance, it requires a lot of computing. More importantly, the segmentation results are not correct in many cases which greatly affect the accuracy of the classification.
The spectrogram is extracted for each heart cycle after the heart cycles are estimated. However, the sizes of the spectrograms are different since the heart rates of different PCG signals are usually not the same. This prohibits a direct comparison between the spectrograms of different PCG signals. A bilinear interpolation [14] method is used to scale the size of the spectrogram, thus enabling the direct comparison. Nevertheless, the scaled spectrogram contains a large quantity of redundant and irrelevant information. In order to extract the most relevant information, a dimension reduction process of the scaled spectrogram is adopted. In addition, the heart sound category provides valuable information to distinguish between different categories and it helps to improve the classification performance. As a result, the extracted features will be more discriminative if the category information is fully utilized during the dimension reduction process. PLSR [15] maximizes the correlation between the PCG signals and their corresponding category information during the dimension reduction process. Thus the category information is utilized. Also, PLSR is capable to robustly handle more descriptor variables than the number of samples. These are the advantage of PLSR compared with other dimensionality reduction method, such as principle component analysis (PCA) [16], linear discriminant analysis (LDA) [17]. Therefore, the discriminative features of the scaled spectrogram are extracted using PLSR in this paper. Finally, the classification is performed using the SVM classifier [11].
The main framework of this paper is shown in Fig. 1 and consists of four steps: estimation of heart cycle duration and alignment, spectrogram scaling of each heart cycle, PLSR and classification. PLSR consists of two parts, i.e., dimension reduction and regression. The contributions of this paper are threefold. First, the heart cycles are estimated and aligned instead of locating both S1 and S2 to simplify the calculation process. Second, the spectrograms of heart cycles of different lengths can be compared directly using the bilinear scaling process which has not been applied in heart sound researches to our knowledge. Third, the category information is utilized during the dimension reduction process. In this way, the extracted features are best correlated with their categories in the dimension reduction process which makes the features more discriminative.
Section snippets
Data collection
The datasets used in this paper, including Dataset-A and Dataset-B [18], are collected from the classifying heart sounds Pascal challenge competition. Dataset-A is collected by volunteers using iStethoscope which is an iPhone application that enables an iPhone to use its microphone as a digital stethoscope [19]. Dataset-A includes 176 records with a 44,100 Hz sampling frequency and it can be grouped into four categories: Normal, Murmur, Extra Heart Sound and Artifact. A normal heart sound has a
Results
The experimental results on the two datasets are compared with the three best methods in the challenge competition: J48 [20], MLP [20] and CS UCL [25]. All the methods are evaluated on the same datasets for the same evaluation criteria.
In the methods of J48 and MLP, only the temporal features are used. The difference is that J48 uses the decision trees as the classifier and MLP uses multi layer perceptron for classification [20]. In the CS UCL method, the wavelet decomposition and spectrogram
Discussion
The objective of this paper is to classify different heart sound signals automatically. Thus, the classification results provide a preliminary diagnosis, which helps to determine whether further diagnosis is necessary. The main categories of heart sounds in this paper are normal, murmur and some problematic heart beats. Their physiological and pathological information is contained in the heart cycles. It is reasonable to use the heart cycles information for classification instead of locating
Conclusion
This paper proposed a novel method for classification based on scaled spectrograms and PLSR. This method can efficiently detect whether a PCG signal is problematic. Thus, it provides valuable information for deciding whether further treatment is necessary. Instead of characterizing the feature of a heart cycle obtained via explicit segmentation, the feature is extracted based on the estimated heart cycle to simplify the computation process. The spectrogram extracted from the heart cycle is
Acknowledgements
This research is partly supported by the National Natural Science Foundation of China under grant Nos. 91120303 and 61471145.
References (26)
- et al.
A history of cardiac auscultation and some of its contributors
Am. J. Cardiol.
(2002) - et al.
A cardiac sound characteristic waveform method for in-home heart disorder monitoring with electric stethoscope
Expert Syst. Appl.
(2006) - et al.
Towards heart sound classification without segmentation via autocorrelation feature and diffusion maps
Future Gener. Comput. Syst.
(2016) - et al.
Segmentation of heart sounds based on dynamic clustering
Biomed. Signal Process. Control
(2012) - et al.
Multi-level basis selection of wavelet packet decomposition tree for heart sound classification
Comput. Biol. Med.
(2013) - et al.
Detection of cardiac abnormality from PCG signal using LMS based least square SVM classifier
Expert Syst. Appl.
(2010) - et al.
Support vectors machine-based identification of heart valve diseases using heart sounds
Comput. Methods Program Biomed.
(2009) - et al.
A robust heart sounds segmentation module based on s-transform
Biomed. Signal Process. Control
(2013) - et al.
Detection of features of prosthetic cardiac valve sound by spectrogram analysis
Appl. Acoust.
(2015) - et al.
Partial least-squares regression: a tutorial
Anal. Chim. Acta
(1986)
Smart phones: new clinical tools in oncology?
Lancet Oncol.
Phonocardiogram signal analysis: a review.
Crit. Rev. Biomed. Eng.
Monitoring cardiac stress using features extracted from s1 heart sounds
IEEE Trans. Biomed. Eng.
Cited by (104)
Hilbert domain characterizations of wavelet packets for automated heart sound abnormality detection
2024, Biomedical Signal Processing and ControlHeart sound classification based on bispectrum features and Vision Transformer mode
2023, Alexandria Engineering JournalDetection of valvular heart diseases combining orthogonal non-negative matrix factorization and convolutional neural networks in PCG signals
2023, Journal of Biomedical InformaticsCombined empirical mode decomposition and phase space reconstruction based psychologically stressed and non-stressed state classification from cardiac sound signals
2023, Biomedical Signal Processing and ControlResearch of heart sound classification using two-dimensional features
2023, Biomedical Signal Processing and Control