Lung Disease Diagnosis Through Mel Spectrogram and Acoustic Feature Analysis

Chronic Obstructive Pulmonary Disease (COPD) is a significant global health challenge, responsible for approximately 3 million deaths annually and ranking as the third leading cause of mortality worldwide. Early detection and diagnosis are crucial to mitigating its impact, but traditional diagnostic tools like MRI, X-rays, and CT scans, while effective, are expensive and require specialized equipment. This makes them less feasible for widespread screening, particularly in resource-limited areas. An alternative approach utilizing lung sounds offers a non-invasive and cost-effective solution. Lung sounds provide critical insights into respiratory health, making them valuable for diagnosing conditions such as COPD, asthma, and pneumonia. However, traditional auscultation with a stethoscope is highly subjective, relying on the expertise of clinicians and prone to variability in diagnosis. These limitations can delay accurate detection, especially in areas lacking experienced healthcare providers. To address this, an automated system is proposed to classify lung sounds using electronic stethoscopes, which ensure superior audio capture. The recordings undergo preprocessing to eliminate noise, followed by conversion into Mel's spectrum representations. These representations mimic human auditory perception, enhancing the system's ability to identify subtle variations in lung sounds. Spectral features derived from the processed data are analyzed to ensure consistent, objective, and accurate diagnostic results, effectively eliminating the subjectivity associated with human interpretation. The proposed system is affordable, portable, and scalable, making it particularly suited for large-scale screenings and early detection in underserved regions. By facilitating timely intervention, it can significantly reduce the global burden of respiratory diseases such as COPD, asthma, and pneumonia. This innovative approach combines cutting-edge technology with practical application, offering a powerful tool to improve respiratory health outcomes worldwide. It underscores the potential of advanced medical techniques in addressing global health challenges while emphasizing accessibility and affordability.

Authors

Publication Details

Published
2025-04-16
DOI
https://doi.org/10.1109/iccct63501.2025.11019006
Primary Topic
Phonocardiography and Auscultation Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Lung Disease Diagnosis Through Mel Spectrogram and Acoustic Feature Analysis

G Shanthakumari, S. Gayathri, E Prajin, J Raamkumar et al.
Phonocardiography and Auscultation Techniques
article

Lung Disease Diagnosis Through Mel Spectrogram and Acoustic Feature Analysis

G Shanthakumari, S. Gayathri, E Prajin, J Raamkumar, M Parvathababu
article en

Abstract

Chronic Obstructive Pulmonary Disease (COPD) is a significant global health challenge, responsible for approximately 3 million deaths annually and ranking as the third leading cause of mortality worldwide. Early detection and diagnosis are crucial to mitigating its impact, but traditional diagnostic tools like MRI, X-rays, and CT scans, while effective, are expensive and require specialized equipment. This makes them less feasible for widespread screening, particularly in resource-limited areas. An alternative approach utilizing lung sounds offers a non-invasive and cost-effective solution. Lung sounds provide critical insights into respiratory health, making them valuable for diagnosing conditions such as COPD, asthma, and pneumonia. However, traditional auscultation with a stethoscope is highly subjective, relying on the expertise of clinicians and prone to variability in diagnosis. These limitations can delay accurate detection, especially in areas lacking experienced healthcare providers. To address this, an automated system is proposed to classify lung sounds using electronic stethoscopes, which ensure superior audio capture. The recordings undergo preprocessing to eliminate noise, followed by conversion into Mel's spectrum representations. These representations mimic human auditory perception, enhancing the system's ability to identify subtle variations in lung sounds. Spectral features derived from the processed data are analyzed to ensure consistent, objective, and accurate diagnostic results, effectively eliminating the subjectivity associated with human interpretation. The proposed system is affordable, portable, and scalable, making it particularly suited for large-scale screenings and early detection in underserved regions. By facilitating timely intervention, it can significantly reduce the global burden of respiratory diseases such as COPD, asthma, and pneumonia. This innovative approach combines cutting-edge technology with practical application, offering a powerful tool to improve respiratory health outcomes worldwide. It underscores the potential of advanced medical techniques in addressing global health challenges while emphasizing accessibility and affordability.

Good health and well-being
Openalex Percentile: Top 78%
Phonocardiography and Auscultation Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Lung Disease Diagnosis Through Mel Spectrogram and Acoustic Feature Analysis — G Shanthakumari, S. Gayathri, et al. · (2025) | TGRS Research Map | TGRS