Research on Segmentation and Classification of Heart Sound Signals Based on Deep Learning

Cardiac murmur grading and risk analysis of cardiac diseases based on adaptable heterogeneous-modality multi-task learning

Cardiovascular disease (CVDs) has become one of the leading causes of death, posing a significant threat to human life. The development of reliable Artificial Intelligence (AI) assisted diagnosis algorithms for cardiac sounds is of great significance for early detection and treatment of CVDs. However, there is scarce research in this field. Existing research mainly faces three major challenges: (1) They mainly limited to murmur classification and cannot achieve murmur grading, but attempting both classification and grading may lead to negative effects between different multi-tasks. (2) They mostly pay attention to unstructured cardiac sound modality and do not consider the structured demographic modality, as it is difficult to balance the influence of heterogeneous modalities. (3) Deep learning methods lack interpretability, which makes it challenging to apply them clinically. To tackle these challenges, we propose a method for cardiac murmur grading and cardiac risk analysis based on heterogeneous modality adaptive multi-task learning. Specifically, a Hierarchical Multi-Task learning-based cardiac murmur detection and grading method (HMT) is proposed to prevent negative interference between different tasks. In addition, a cardiac risk analysis method based on Heterogeneous Multi-modal feature impact Adaptation (HMA) is also proposed, which transforms unstructured modality into structured modality representation, and utilizes an adaptive mode weight learning mechanism to balance the impact between unstructured modality and structured modality, thus enhancing the performance of cardiac risk prediction. Finally, we propose a multi-task interpretability learning module that incorporates an important evaluation using random masks. This module utilizes SHAP graphs to visualize crucial murmur segments in cardiac sound and employs a multi-factor risk decoupling model based on nomograms. And then we gain insights into the cardiac disease risk in both pre-decoupled multi-modality and post-decoupled single-modality scenarios, thus providing a solid foundation for AI assisted cardiac murmur grading and risk analysis. Experimental results on a large real-world CirCor DigiScope PCG dataset demonstrate that the proposed method outperforms the state-of-the-art (SOTA) method in murmur detection, grading, and cardiac risk analysis, while also providing valuable diagnostic evidence.

Segmentation of Heart Sound Signal Based on Multi-Scale Feature Fusion and Multi-Classification of Congenital Heart Disease

Analyzing heart sound signals presents a novel approach for early diagnosis of pediatric congenital heart disease. The existing segmentation algorithms have limitations in accurately distinguishing the first (S1) and second (S2) heart sounds, limiting the diagnostic utility of cardiac cycle data for pediatric pathology assessment. This study proposes a time bidirectional long short-term memory network (TBLSTM) based on multi-scale analysis to segment pediatric heart sound signals according to different cardiac cycles. Mel frequency cepstral coefficients and dynamic characteristics of the heart sound fragments were extracted and input into random forest for multi-classification of congenital heart disease. The segmentation model achieved an overall F1 score of 94.15% on the verification set, with specific F1 scores of 90.25% for S1 and 86.04% for S2. In a situation where the number of cardiac cycles in the heart sound fragments was set to six, the results for multi-classification achieved stabilization. The performance metrics for this configuration were as follows: accuracy of 94.43%, sensitivity of 95.58%, and an F1 score of 94.51%. Furthermore, the segmentation model demonstrates robustness in accurately segmenting pediatric heart sound signals across different heart rates and in the presence of noise. Notably, the number of cardiac cycles in heart sound fragments directly impacts the multi-classification of these heart sound signals.

Advances in Portable and Wearable Acoustic Sensing Devices for Human Health Monitoring

The practice of auscultation, interpreting body sounds to assess organ health, has greatly benefited from technological advancements in sensing and electronics. The advent of portable and wearable acoustic sensing devices marks a significant milestone in telemedicine, home health, and clinical diagnostics. This review summarises the contemporary advancements in acoustic sensing devices, categorized based on varied sensing principles, including capacitive, piezoelectric, and triboelectric mechanisms. Some representative acoustic sensing devices are introduced from the perspective of portability and wearability. Additionally, the characteristics of sound signals from different human organs and practical applications of acoustic sensing devices are exemplified. Challenges and prospective trends in portable and wearable acoustic sensors are also discussed, providing insights into future research directions.

An Optimal Approach for Heart Sound Classification Using Grid Search in Hyperparameter Optimization of Machine Learning

Heart-sound auscultation is one of the most widely used approaches for detecting cardiovascular disorders. Diagnosing abnormalities of heart sound using a stethoscope depends on the physician's skill and judgment. Several studies have shown promising results in automatically detecting cardiovascular disorders based on heart-sound signals. However, the accuracy performance needs to be enhanced as automated heart-sound classification aids in the early detection and prevention of the dangerous effects of cardiovascular problems. In this study, an optimal heart-sound classification method based on machine learning technologies for cardiovascular disease prediction is performed. It consists of three steps: pre-processing that sets the 5 s duration of the PhysioNet Challenge 2016 and 2022 datasets, feature extraction using Mel frequency cepstrum coefficients (MFCC), and classification using grid search for hyperparameter tuning of several classifier algorithms including k-nearest neighbor (K-NN), random forest (RF), artificial neural network (ANN), and support vector machine (SVM). The five-fold cross-validation was used to evaluate the performance of the proposed method. The best model obtained classification accuracy of 95.78% and 76.31%, which was assessed using PhysioNet Challenge 2016 and 2022, respectively. The findings demonstrate that the suggested approach obtained excellent classification results using PhysioNet Challenge 2016 and showed promising results using PhysioNet Challenge 2022. Therefore, the proposed method has been potentially developed as an additional tool to facilitate the medical practitioner in diagnosing the abnormality of the heart sound.

A Decision Support System for Melanoma Diagnosis from Dermoscopic Images

Innovative technologies in dermatology allow for the early screening of skin cancer, which results in a reduction in the mortality rate and surgical treatments. The diagnosis of melanoma is complex not only because of the number of different lesions but because of the high similarity amongst skin lesions of different nature; hence, human vision and physician experience still play a major role. The adoption of automatic systems would aid clinical assessment and make the diagnosis reproducible by eliminating inter- and intra-observer variabilities. In our paper, we describe a computer-aided system for the early diagnosis of melanoma in dermoscopic images. A soft pre-processing phase is performed so as to avoid the loss of details both in texture, colors, and contours, and color-based image segmentation is later carried out using k-means. Features linked to both geometric properties and color characteristics are used to analyze skin lesions through a support vector machine classifier. The PH2 public database is used for the assessment of the procedure’s sensitivity, specificity, and accuracy. A statistical approach is carried out to establish the impact of image quality on performance. The obtained results show remarkable achievements, so our computer-aided approach should be suitable as a Decision Support System for melanoma detection.

Deep Learning-Based Heart Sound Analysis for Left Ventricular Diastolic Dysfunction Diagnosis

The aggravation of left ventricular diastolic dysfunction (LVDD) could lead to ventricular remodeling, wall stiffness, reduced compliance, and progression to heart failure with a preserved ejection fraction. A non-invasive method based on convolutional neural networks (CNN) and heart sounds (HS) is presented for the early diagnosis of LVDD in this paper. A deep convolutional generative adversarial networks (DCGAN) model-based data augmentation (DA) method was proposed to expand a HS database of LVDD for model training. Firstly, the preprocessing of HS signals was performed using the improved wavelet denoising method. Secondly, the logistic regression based hidden semi-Markov model was utilized to segment HS signals, which were subsequently converted into spectrograms for DA using the short-time Fourier transform (STFT). Finally, the proposed method was compared with VGG-16, VGG-19, ResNet-18, ResNet-50, DenseNet-121, and AlexNet in terms of performance for LVDD diagnosis. The result shows that the proposed method has a reasonable performance with an accuracy of 0.987, a sensitivity of 0.986, and a specificity of 0.988, which proves the effectiveness of HS analysis for the early diagnosis of LVDD and demonstrates that the DCGAN-based DA method could effectively augment HS data.