Deep learning-based lung sound analysis for intelligent stethoscope

Military Medical Research, Journal Year: 2023, Volume and Issue: 10(1)

Published: Sept. 26, 2023

Abstract Auscultation is crucial for the diagnosis of respiratory system diseases. However, traditional stethoscopes have inherent limitations, such as inter-listener variability and subjectivity, they cannot record sounds offline/retrospective or remote prescriptions in telemedicine. The emergence digital has overcome these limitations by allowing physicians to store share consultation education. On this basis, machine learning, particularly deep enables fully-automatic analysis lung that may pave way intelligent stethoscopes. This review thus aims provide a comprehensive overview learning algorithms used sound emphasize significance artificial intelligence (AI) field. We focus on each component learning-based systems, including task categories, public datasets, denoising methods, and, most importantly, existing i.e., state-of-the-art approaches convert into two-dimensional (2D) spectrograms use convolutional neural networks end-to-end recognition diseases abnormal sounds. Additionally, highlights current challenges field, variety devices, noise sensitivity, poor interpretability models. To address reproducibility also provides scalable flexible open-source framework standardize algorithmic workflow solid basis replication future extension: https://github.com/contactless-healthcare/Deep-Learning-for-Lung-Sound-Analysis .

Language: Английский

---

Lung Sound Classification With Multi-Feature Integration Utilizing Lightweight CNN Model

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 21262 - 21276

Published: Jan. 1, 2024

Detecting respiratory diseases is of utmost importance, considering that ailments represent one the most prevalent categories globally. The initial stage lung disease detection involves auscultation conducted by specialists, relying significantly on their expertise. Therefore, automating process for can yield enhanced efficiency. Artificial intelligence (AI) has shown promise in improving accuracy sound classification extracting features from sounds are relevant to task and learning relationships between these different pulmonary diseases. This paper utilizes two publicly available recordings namely, ICBHI 2017 challenge dataset another at Mendeley Data. Foremost this paper, we provide a detailed exposition about employing Convolutional Neural Network (CNN) feature extraction Mel spectrograms, frequency cepstral coefficients (MFCCs), Chromagram. highest achieved developed 91.04% 10 classes. Extending contribution, elaborates explanation model prediction Explainable Intelligence (XAI). novel contribution study CNN classifies into classes combining audio-specific enhance process.

Language: Английский

---

Respiratory sound classification utilizing human auditory-based feature extraction.

Physica Scripta, Journal Year: 2025, Volume and Issue: 100(4), P. 046003 - 046003

Published: Feb. 19, 2025

Abstract A major worldwide health concern is chronic respiratory diseases (CRDs), which include disorders including asthma, pulmonary hypertension, occupational lung diseases, and obstructive disease (COPD). Improving clinical results treatment efficacy requires an early precise diagnosis. In order to classify sounds, this study presents a novel framework that incorporates auditory-inspired characteristics, such as Mel-Frequency Cepstral Coefficients (MFCCs), Mel Spectrograms, Cochleograms, into CNN-LSTM architecture. The uses sophisticated feature extraction techniques in conjunction with strong data augmentation approaches address the issue of class imbalance guarantee thorough representation variety sound patterns. Using Respiratory Sound Database, suggested model was assessed showed remarkable performance, obtaining F1 score 98.94%, accuracy 98.90%, specificity 99.80%, sensitivity ICBHI 99.40%. These findings demonstrate model’s potential reliable efficient tool for identification evaluation CRDs, would significantly improve patient care management illnesses. outstanding performance further emphasizes importance settings, enabling improved conditions.

Language: Английский

---

Detection of various lung diseases including COVID-19 using extreme learning machine algorithm based on the features extracted from a lightweight CNN architecture

Journal of Applied Biomedicine, Journal Year: 2023, Volume and Issue: 43(3), P. 528 - 550

Published: June 26, 2023

Around the world, several lung diseases such as pneumonia, cardiomegaly, and tuberculosis (TB) contribute to severe illness, hospitalization or even death, particularly for elderly medically vulnerable patients. In last few decades, new types of lung-related have taken lives millions people, COVID-19 has almost 6.27 million lives. To fight against diseases, timely correct diagnosis with appropriate treatment is crucial in current pandemic. this study, an intelligent recognition system seven been proposed based on machine learning (ML) techniques aid medical experts. Chest X-ray (CXR) images were collected from publicly available databases. A lightweight convolutional neural network (CNN) used extract characteristic features raw pixel values CXR images. The best feature subset identified using Pearson Correlation Coefficient (PCC). Finally, extreme (ELM) perform classification task assist faster reduced computational complexity. CNN-PCC-ELM model achieved accuracy 96.22% Area Under Curve (AUC) 99.48% eight class classification. outcomes demonstrated better performance than existing state-of-the-art (SOTA) models case COVID-19, detection both binary multiclass classifications. For classification, precision, recall fi-score ROC are 100%, 99%, 100% 99.99% respectively demonstrating its robustness. Therefore, overshadowed pioneering accurately differentiate other that can physicians treating patient effectively.

Language: Английский

---

Research on lung sound classification model based on dual-channel CNN-LSTM algorithm

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 94, P. 106257 - 106257

Published: March 25, 2024

ulmonary diseases have a significant impact on human health and life safety, abnormalities in the lungs are direct response to lung diseases. Establishing an effective sound classification model that can assist diagnosis is of great significance for electronic auscultation.In addressing issue signal classification, this study introduces deep learning based dual-channel CNN-LSTM algorithm. Initially, Mel-scale Frequency Cepstral Coefficients (MFCC) employed feature extraction from dataset, transforming signals into Mel spectrograms. On foundation, algorithm constructed, with parallel Convolutional Neural Network (CNN) Long Short-Term Memory (LSTM) modules. The CNN module designed capture spatial dimension features input data, while LSTM focuses temporal features. These two sets fused together, enabling classify sounds thereby assisting diagnosing pulmonary healthcare practitioners. This experiment used ICBHI2017 Challenge Lungs dataset obtained 5054 pieces data through augmentation sampling techniques.The results show accuracy, recall, F1 score reach 99.01%, 99.13%, 0.9915, respectively, significantly superior other models, highlighting its practical application value.

Language: Английский

---

Reviewing CAM-Based Deep Explainable Methods in Healthcare

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(10), P. 4124 - 4124

Published: May 13, 2024

The use of artificial intelligence within the healthcare sector is consistently growing. However, majority deep learning-based AI systems are a black box nature, causing these to suffer from lack transparency and credibility. Due widespread adoption medical imaging for diagnostic purposes, industry frequently relies on methods that provide visual explanations, enhancing interpretability. Existing research has summarized explored usage explanation in domain, providing introductions have been employed. existing reviews used interpretable analysis field ignoring comprehensive Class Activation Mapping (CAM) because researchers typically categorize CAM under broader umbrella explanations without delving into specific applications sector. Therefore, this study primarily aims analyze CAM-based explainable industry, following PICO (Population, Intervention, Comparison, Outcome) framework. Specifically, we selected 45 articles systematic review comparative three databases—PubMed, Science Direct, Web Science—and then compared eight advanced using five datasets assist method selection. Finally, current hotspots future challenges application field.

Language: Английский

---

Deep transfer learning rolling bearing fault diagnosis method based on convolutional neural network feature fusion

Measurement Science and Technology, Journal Year: 2023, Volume and Issue: 35(1), P. 015013 - 015013

Published: Sept. 28, 2023

Abstract Current deep-learning methods are often based on significantly large quantities of labeled fault data for supervised training. In practice, it is difficult to obtain samples rolling bearing failures. this paper, a transfer learning-based feature fusion convolutional neural network approach diagnosis proposed. Specifically, the raw vibration signal features and corresponding time-frequency image input extracted by one-dimensional pre-trained ConvNeXt, respectively, connected strategy. Then, fine-tuning method learning can effectively reduce reliance in target domain. A wide convolution kernel introduced time-domain extraction increase receptive field, which combined with channel attention mechanism further optimize quality. Finally, two common datasets utilized experiments. The experimental results show that proposed model achieves an average accuracy more than 98.63% both cross-working conditions cross-device tasks. Meanwhile, anti-noise experiments ablation validate robustness method.

Language: Английский

---

A deep CNN-based acoustic model for the identification of lung diseases utilizing extracted MFCC features from respiratory sounds

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: 83(35), P. 82871 - 82903

Published: March 12, 2024

Language: Английский

---

Auscultation-Based Pulmonary Disease Detection through Parallel Transformation and Deep Learning

Bioengineering, Journal Year: 2024, Volume and Issue: 11(6), P. 586 - 586

Published: June 8, 2024

Respiratory diseases are among the leading causes of death, with many individuals in a population frequently affected by various types pulmonary disorders. Early diagnosis and patient monitoring (traditionally involving lung auscultation) essential for effective management respiratory diseases. However, interpretation sounds is subjective labor-intensive process that demands considerable medical expertise, there good chance misclassification. To address this problem, we propose hybrid deep learning technique incorporates signal processing techniques. Parallel transformation applied to adventitious sounds, transforming sound signals into two distinct time-frequency scalograms: continuous wavelet transform mel spectrogram. Furthermore, parallel convolutional autoencoders employed extract features from scalograms, resulting latent space fused feature pool. Finally, leveraging long short-term memory model, used as input classifying Our work evaluated using ICBHI-2017 dataset. The experimental findings indicate our proposed method achieves promising predictive performance, average values accuracy, sensitivity, specificity, F1-score 94.16%, 89.56%, 99.10%, respectively, eight-class diseases; 79.61%, 78.55%, 92.49%, 78.67%, four-class 85.61%, 83.44%, 84.21%, binary-class (normal vs. abnormal) sounds.

Language: Английский

---

Deep recurrent learning based qualified sequence segment analytical model (QS2AM) for infectious disease detection using CT images

Evolving Systems, Journal Year: 2023, Volume and Issue: 15(2), P. 505 - 521

Published: Dec. 23, 2023

Language: Английский

---