Abstract:The goal of the 2016 PhysioNet/CinC Challenge is the development of an algorithm to classify normal/abnormal heart sounds. A total of 124 time-frequency features were extracted from the phonocardiogram (PCG) and input to a variant of the AdaBoost classifier. A second classifier using convolutional neural network (CNN) was trained using PCGs cardiac cycles decomposed into four frequency bands. The final decision rule to classify normal/abnormal heart sounds was based on an ensemble of classifiers combining the … Show more
“…Applications of DL to cardiac signals are introduced very recently [6][7][8]. CNNs have been used for normal/abnormal PCG classification using input features such as spectrogram and Mel-frequency cepstrum coefficients (MFCCs) in [9] on 5-second windowed segments, and MFCC heatmaps of 3-second segments in [10].…”
This paper proposes a framework based on deep convolutional neural networks (CNNs) for automatic heart sound classification using short-segments of individual heart beats. We design a 1D-CNN that directly learns features from raw heart-sound signals, and a 2D-CNN that takes inputs of twodimensional time-frequency feature maps based on Mel-frequency cepstral coefficients (MFCC). We further develop a time-frequency CNN ensemble (TF-ECNN) combining the 1D-CNN and 2D-CNN based on score-level fusion of the class probabilities. On the large PhysioNet CinC challenge 2016 database, the proposed CNN models outperformed traditional classifiers based on support vector machine and hidden Markov models with various hand-crafted time-and frequency-domain features. Best classification scores with 89.22% accuracy and 89.94% sensitivity were achieved by the ECNN, and 91.55% specificity and 88.82% modified accuracy by the 2D-CNN alone on the test set.
“…Applications of DL to cardiac signals are introduced very recently [6][7][8]. CNNs have been used for normal/abnormal PCG classification using input features such as spectrogram and Mel-frequency cepstrum coefficients (MFCCs) in [9] on 5-second windowed segments, and MFCC heatmaps of 3-second segments in [10].…”
This paper proposes a framework based on deep convolutional neural networks (CNNs) for automatic heart sound classification using short-segments of individual heart beats. We design a 1D-CNN that directly learns features from raw heart-sound signals, and a 2D-CNN that takes inputs of twodimensional time-frequency feature maps based on Mel-frequency cepstral coefficients (MFCC). We further develop a time-frequency CNN ensemble (TF-ECNN) combining the 1D-CNN and 2D-CNN based on score-level fusion of the class probabilities. On the large PhysioNet CinC challenge 2016 database, the proposed CNN models outperformed traditional classifiers based on support vector machine and hidden Markov models with various hand-crafted time-and frequency-domain features. Best classification scores with 89.22% accuracy and 89.94% sensitivity were achieved by the ECNN, and 91.55% specificity and 88.82% modified accuracy by the 2D-CNN alone on the test set.
“…We use two different baseline models for performance comparison: (i) the top-scoring method from the INTERSPEECH 2018 ComParE Heart Beats Sub-Challenge by Gabor et al [16] as a traditional machine learning baseline, and (ii) the best performing system in the Physionet 2016 CinC Challenge developed by Potes et al [13] as a deep learning baseline.…”
Section: B Baselines Methods and Implementationmentioning
confidence: 99%
“…The BoAW ensemble and the Fusion framework are denoted by Gabor-BoAW-SVC and Gabor-Fusion-SVC, respectively. The branched CNN model by Potes et al [13] (Potes-CNN) is implemented as our deep learning baseline system. It has a static front-end FIR filterbank as the input and provides inferences for each segmented cardiac cycles.…”
Section: B Baselines Methods and Implementationmentioning
confidence: 99%
“…6 and 7 show the front-end FIR filter coefficients from different methods and their magnitude/phase responses, respectively. All of the learnable filterbanks are initialized with static FIR coefficients [13] except for the gammatone tConv units. The gammatone tConv is initialized with α k = 10 5 and η k = 4, while f k ∼ U(10, 400) and β k ∼ N (30, 6 2 ) are randomly sampled from a uniform and a normal distribution, respectively.…”
Section: E Interpreting the Learnable Filterbanksmentioning
confidence: 99%
“…Notable features reported for this dataset includes, time, frequency and statistical features [8], Mel-frequency Cepstral Coefficients (MFCC) [9], and Continuous Wavelet Transform (CWT) [10]. Classifiers like SVM [11], k-Nearest Neighbor (k-NN) [9], Multilayer Perceptron (MLP) [10], [12] and Random Forest [8], deep learning approaches with 1D & 2D CNNs [13], [14], and Recurrent Neural Network (RNN) [15] based architectures were employed in the challenge submissions. The winning algorithm, similar to a good number of other submissions, proposed an ensemble; a static filter front-end 1D-CNN model combined with an Adaboost-Abstain classifier using a threshold-based voting algorithm.…”
Objective: Cardiac auscultation is the most practiced non-invasive and cost-effective procedure for the early diagnosis of heart diseases. While machine learning based systems can aid in automatically screening patients, the robustness of these systems is affected by numerous factors including the stethoscope/sensor, environment and data collection protocol. This paper studies the adverse effect of domain variability on heart sound classification and develops strategies to address this problem. Methods: We propose a novel Convolutional Neural Network (CNN) layer, consisting of time-convolutional (tConv) units, that emulate Finite Impulse Response (FIR) filters. The filter coefficients can be updated via backpropagation and be stacked in the front-end of the network as a learnable filterbank. These filters can incorporate properties such as linear/zero phase-response and symmetry while improving robustness due to domain variability. Results: Our methods are evaluated using multi-domain heart sound recordings obtained from publicly available phonocardiogram (PCG) datasets. On multi-domain evaluation tasks, the proposed method surpasses the top-scoring systems found in the literature for heart sound classification. Our systems achieved relative improvements of up to 11.84% in terms of a modified accuracy (Macc) metric, compared to state-of-theart methods. Conclusion: The results demonstrate the effectiveness of the proposed learnable filterbank CNN architecture in achieving robustness towards sensor/domain variability in PCG signals. Significance: The proposed methods pave the way for deploying automated cardiac screening systems in diversified and underserved communities.
This paper proposes a pre‐processing method for heart sound screening and extracts the high‐order spectral feature of phonocardiogram. Moreover, a multi‐convolutional neural network (mCNN) is constructed to achieve the classification of normal, aortic stenosis, mitral regurgitation, mitral stenosis, and mitral valve prolapse. First, the heart sound recordings are down‐sampled, denoised by wavelet transform, and normalized. Second, a new heart sound screening algorithm is proposed. The waveform of the heart sound recording is segmented and saved as an image which is performed by the gray‐scale processing to calculate the amplitude of the heart sound. The extremely noisy heart sound segments are screened out based on the amplitude information, and the remaining heart sound segments are spliced as pure heart sound recordings. After 50% superposition segmentation of the heart sound recordings, high‐order spectral features are extracted and image data are stored. Finally, a 34‐layer mCNN is specifically designed to boost the performance of heart sound classification through multi‐layer dimensionality reduction. Experimental results show that the proposed method has superior performance compared with the existing one. For the two‐category dataset, the accuracy with and without PCG screening is 97.99% and 99.42%, respectively. For the five‐category dataset, the average accuracy is 99%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.