TY - JOUR
T1 - Automatic Multi-Level In-Exhale Segmentation and Enhanced Generalized S-Transform for wheezing detection
AU - Chen, Hai
AU - Yuan, Xiaochen
AU - Li, Jianqing
AU - Pei, Zhiyuan
AU - Zheng, Xiaobin
N1 - Publisher Copyright:
© 2019 Elsevier B.V.
PY - 2019/9
Y1 - 2019/9
N2 - Background and objective: Wheezing is a common symptom of patients caused by asthma and chronic obstructive pulmonary diseases. Wheezing detection identifies wheezing lung sounds and helps physicians in diagnosis, monitoring, and treatment of pulmonary diseases. Different from the traditional way to detect wheezing sounds using digital image process methods, automatic wheezing detection uses computerized tools or algorithms to objectively and accurately assess and evaluate lung sounds. We propose an innovative machine learning-based approach for wheezing detection. The phases of the respiratory sounds are separated automatically and the wheezing features are extracted accordingly to improve the classification accuracy. Methods: To enhance the features of wheezing for classification, the Adaptive Multi-Level In-Exhale Segmentation (AMIE_SEG) is proposed to automatically and precisely segment the respiratory sounds into inspiratory and expiratory phases. Furthermore, the Enhanced Generalized S-Transform (EGST) is proposed to extract the wheezing features. The highlighted features of wheezing improve the accuracy of wheezing detection with machine learning-based classifiers. Results: To evaluate the novelty and superiority of the proposed AMIE_SEG and EGST for wheezing detection, we employ three machine learning-based classifiers, Support Vector Machine (SVM), Extreme Learning Machine (ELM) and K-Nearest Neighbor (KNN), with public datasets at segment level and record level respectively. According to the experimental results, the proposed method performs the best using the KNN classifier at segment level, with the measured accuracy, sensitivity, specificity as 98.62%, 95.9% and 99.3% in average respectively. On the other aspect, at record level, the three classifiers perform excellent, with the accuracy, sensitivity, specificity up to 99.52%, 100% and 99.27% respectively. We validate the method with public respiratory sounds dataset. Conclusion: The comparison results indicate the very good performance of the proposed methods for long-term wheezing monitoring and telemedicine.
AB - Background and objective: Wheezing is a common symptom of patients caused by asthma and chronic obstructive pulmonary diseases. Wheezing detection identifies wheezing lung sounds and helps physicians in diagnosis, monitoring, and treatment of pulmonary diseases. Different from the traditional way to detect wheezing sounds using digital image process methods, automatic wheezing detection uses computerized tools or algorithms to objectively and accurately assess and evaluate lung sounds. We propose an innovative machine learning-based approach for wheezing detection. The phases of the respiratory sounds are separated automatically and the wheezing features are extracted accordingly to improve the classification accuracy. Methods: To enhance the features of wheezing for classification, the Adaptive Multi-Level In-Exhale Segmentation (AMIE_SEG) is proposed to automatically and precisely segment the respiratory sounds into inspiratory and expiratory phases. Furthermore, the Enhanced Generalized S-Transform (EGST) is proposed to extract the wheezing features. The highlighted features of wheezing improve the accuracy of wheezing detection with machine learning-based classifiers. Results: To evaluate the novelty and superiority of the proposed AMIE_SEG and EGST for wheezing detection, we employ three machine learning-based classifiers, Support Vector Machine (SVM), Extreme Learning Machine (ELM) and K-Nearest Neighbor (KNN), with public datasets at segment level and record level respectively. According to the experimental results, the proposed method performs the best using the KNN classifier at segment level, with the measured accuracy, sensitivity, specificity as 98.62%, 95.9% and 99.3% in average respectively. On the other aspect, at record level, the three classifiers perform excellent, with the accuracy, sensitivity, specificity up to 99.52%, 100% and 99.27% respectively. We validate the method with public respiratory sounds dataset. Conclusion: The comparison results indicate the very good performance of the proposed methods for long-term wheezing monitoring and telemedicine.
KW - Adaptive Multi-Level In-Exhale Segmentation (AMIE_SEG)
KW - Enhanced Generalized S Transform
KW - Feature enhancement
KW - Wheezing detection
UR - http://www.scopus.com/inward/record.url?scp=85068065422&partnerID=8YFLogxK
U2 - 10.1016/j.cmpb.2019.06.024
DO - 10.1016/j.cmpb.2019.06.024
M3 - Article
C2 - 31416545
AN - SCOPUS:85068065422
SN - 0169-2607
VL - 178
SP - 163
EP - 173
JO - Computer Methods and Programs in Biomedicine
JF - Computer Methods and Programs in Biomedicine
ER -