Interpretation of lung disease classification with light attention connected module

Biomedical Signal Processing and Control, Journal Year: 2023, Volume and Issue: 84, P. 104695 - 104695

Published: March 2, 2023

Language: Английский

---

Incorporating support vector machine to the classification of respiratory sounds by Convolutional Neural Network

Biomedical Signal Processing and Control, Journal Year: 2022, Volume and Issue: 79, P. 104093 - 104093

Published: Aug. 20, 2022

Language: Английский

---

Automated Detection of Pulmonary Diseases From Lung Sound Signals Using Fixed-Boundary-Based Empirical Wavelet Transform

IEEE Sensors Letters, Journal Year: 2022, Volume and Issue: 6(5), P. 1 - 4

Published: April 13, 2022

In this letter, a promising method is proposed to automatically detect pulmonary diseases (PDs) from lung sound (LS) signals. The modes of the LS signal are evaluated using empirical wavelet transform with fixed boundary points. time-domain (Shannon entropy) and frequency-domain (peak amplitude peak frequency) features have been extracted each mode. classifiers, such as support vector machine, random forest, extreme gradient boosting, light boosting machine (LGBM), chosen PDs signals automatically. performance has obtained publicly available database. detection accuracy values, 80.35, 83.27, 99.34, 77.13%, LGBM classifier fivefold cross validation for normal versus asthma, pneumonia, chronic obstructive disease (COPD), pneumonia asthma COPD classification schemes. For scheme, achieved an value 84.76%, which higher than that existing approaches

Language: Английский

---

A review on lung disease recognition by acoustic signal analysis with deep learning networks

Journal Of Big Data, Journal Year: 2023, Volume and Issue: 10(1)

Published: June 12, 2023

Abstract Recently, assistive explanations for difficulties in the health check area have been made viable thanks considerable portion to technologies like deep learning and machine learning. Using auditory analysis medical imaging, they also increase predictive accuracy prompt early disease detection. Medical professionals are thankful such technological support since it helps them manage further patients because of shortage skilled human resources. In addition serious illnesses lung cancer respiratory diseases, plurality breathing is gradually rising endangering society. Because prediction immediate treatment crucial disorders, chest X-rays sound audio proving be quite helpful together. Compared related review studies on classification/detection using algorithms, only two based signal diagnosis conducted 2011 2018. This work provides a recognition with acoustic networks. We anticipate that physicians researchers working sound-signal-based will find this material beneficial.

Language: Английский

---

Cochleogram-based adventitious sounds classification using convolutional neural networks

Biomedical Signal Processing and Control, Journal Year: 2023, Volume and Issue: 82, P. 104555 - 104555

Published: Jan. 5, 2023

The World Health Organization (WHO) establishes as a top priority the early detection of respiratory diseases. This could be performed by means recognizing presence acoustic bio-markers (adventitious sounds) from auscultation because it is still main technique applied in any health center to assess status system due its non-invasive, low-cost, easy apply, fast diagnose and safe nature. Despite novel deep learning approaches this biomedical field, there notable lack research that rigorously focuses on different time–frequency representations determine most suitable transformation feed data into Convolutional Neural Network (CNN) architectures. In paper, we propose use cochleogram, based modeling frequency selectivity human cochlea, an improved representation optimize process CNN model classification adventitious sounds. Our proposal evaluated using largest challenging public database cochleogram obtains best binary results among compared methods with average accuracy 85.1% wheezes 73.8% crackles, competitive performance evaluating multiclass scenario comparison other well-known state-of-the-art models. provides since able content more accurately non-uniform spectral resolution increased robustness noise changes. fact implies significant improvement models

Language: Английский

---

Classification of Adventitious Sounds Combining Cochleogram and Vision Transformers

Sensors, Journal Year: 2024, Volume and Issue: 24(2), P. 682 - 682

Published: Jan. 21, 2024

Early identification of respiratory irregularities is critical for improving lung health and reducing global mortality rates. The analysis sounds plays a significant role in characterizing the system's condition identifying abnormalities. main contribution this study to investigate performance when input data, represented by cochleogram, used feed Vision Transformer architecture, since classifier combination first time it has been applied adventitious sound classification our knowledge. Although ViT shown promising results audio tasks applying self attention spectrogram patches, we extend approach which captures specific spectro-temporal features sounds. proposed methodology evaluated on ICBHI dataset. We compare with other state art CNN approaches using spectrogram, Mel frequency cepstral coefficients, constant Q transform, cochleogram as data. Our confirm superior combining ViT, highlighting potential reliable classification. This contributes ongoing efforts developing automatic intelligent techniques aim significantly augment speed effectiveness disease detection, thereby addressing need medical field.

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

---

Machine Learning for Automated Classification of Abnormal Lung Sounds Obtained from Public Databases: A Systematic Review

Bioengineering, Journal Year: 2023, Volume and Issue: 10(10), P. 1155 - 1155

Published: Oct. 2, 2023

Pulmonary auscultation is essential for detecting abnormal lung sounds during physical assessments, but its reliability depends on the operator. Machine learning (ML) models offer an alternative by automatically classifying sounds. ML require substantial data, and public databases aim to address this limitation. This systematic review compares characteristics, diagnostic accuracy, concerns, data sources of existing in literature. Papers published from five major between 1990 2022 were assessed. Quality assessment was accomplished with a modified QUADAS-2 tool. The encompassed 62 studies utilizing public-access sound classification. Artificial neural networks (ANN) support vector machines (SVM) frequently employed classifiers. accuracy ranged 49.43% 100% discriminating types 69.40% 99.62% disease class Seventeen identified, ICBHI 2017 database being most used (66%). majority exhibited high risk bias concerns related patient selection reference standards. Summarizing, can effectively classify using publicly available sources. Nevertheless, inconsistent reporting methodologies pose limitations advancing field, therefore, should adhere standardized recording labeling procedures.

Language: Английский

---

Automatic Analysis of Lung Sounds in 3‐Year‐Old Children

Pediatric Pulmonology, Journal Year: 2025, Volume and Issue: 60(4)

Published: April 1, 2025

In recent years, with the advent of artificial intelligence, clear progress has been made in clinical application lung sound analysis techniques. Using a new software program to analyze pediatric sounds using machine learning (ML), we conducted survey study 139 healthy 3-year-old children. All cases were surveyed ATS-DLD questionnaire, which mainly included items related history wheezing, diagnosis asthma, and respiratory syncytial virus (RSV) infection, allergies environment. The characteristics examined, along results questionnaire parameters. Children wheezing showed higher maximum inspiratory frequency (FAP0), lower basal power (PAP0) (p < 0.001 p 0.001, respectively), RPF50p RPF75p = 0.003 0.003, suggesting enhancement high-pitched region spectrum. A similar tendency was observed children asthma or RSV infection. Furthermore, group those acute tract infection (ARI) within 1 week found have an relative without ARI. By utilizing ML, that suspected had characteristic even when healthy.

Language: Английский

---

Machine learning-driven strategies for enhanced pediatric wheezing detection

Frontiers in Pediatrics, Journal Year: 2025, Volume and Issue: 13

Published: May 20, 2025

Background Auscultation is a critical diagnostic feature of lung diseases, but it subjective and challenging to measure accurately. To overcome these limitations, artificial intelligence models have been developed. Methods In this prospective study, we aimed compare respiratory sound extraction methods develop an optimal machine learning model for detecting wheezing in children. Pediatric pulmonologists recorded verified 103 instances 184 other sounds 76 Various were used extraction, dimensions reduced using t-distributed Stochastic Neighbor Embedding (t-SNE). The performance detection was evaluated kernel support vector (SVM). Results duration recordings the non-wheezing groups 89.36 ± 39.51 ms 63.09 27.79 ms, respectively. Mel-spectrogram, Mel-frequency Cepstral Coefficient (MFCC), spectral contrast achieved best expression showed good cluster classification. SVM exhibited performance, with accuracy, precision, recall, F-1 score 0.897, 0.800, 0.952, 0.869, Conclusion Mel-spectrograms, MFCC, are effective characterizing A demonstrated high indicating its potential utility ensuring accurate diagnosis pediatric diseases.

Language: Английский

---