Presentation Type
Poster
Student
Yes
Track
Health Care Application
Abstract
Abstract. In this paper, we analyze deep visual features from 2D data representation(s) of the respiratory sound to detect evidence of lung abnormalities. The primary motivation behind this is that visual cues are more important in decision-making than raw data (lung sound). Early detection and prompt treatments are essential for any future possible respiratory disorders, and respiratory sound is proven to be one of the biomarkers. In contrast to state-of-the-art approaches, we aim at understanding/analyzing visual features using our Convolutional Neural Networks (CNN) tailored Deep Learning Models, where we consider all possible 2D data such as Spectrogram, Mel-frequency Cepstral Coefficients (MFCC), spectral centroid, and spectral roll-off. In our experiments, using the publicly available respiratory sound database named ICBHI 2017 (5.5 hours of recordings containing 6898 respiratory cycles from 126 subjects), we received the highest performance with the area under the curve of 0.79 from Spectrogram as opposed to 0.48 AUC from the raw data from a pre-trained deep learning model: VGG16. Our study proved that 2D data representation could help better understand/analyze lung abnormalities as compared to 1D data. In addition, our results can be compared with previous works.
Keywords: Lung Abnormality· Respiratory Sound · 2D Data Representation · Deep Visual Features.
Start Date
2-7-2023 1:00 PM
End Date
2-7-2023 2:00 PM
Included in
Bioinformatics Commons, Biomedical Informatics Commons, Data Science Commons, Vision Science Commons
2D Respiratory Sound Analysis to Detect Lung Abnormalities
Volstorff A
Abstract. In this paper, we analyze deep visual features from 2D data representation(s) of the respiratory sound to detect evidence of lung abnormalities. The primary motivation behind this is that visual cues are more important in decision-making than raw data (lung sound). Early detection and prompt treatments are essential for any future possible respiratory disorders, and respiratory sound is proven to be one of the biomarkers. In contrast to state-of-the-art approaches, we aim at understanding/analyzing visual features using our Convolutional Neural Networks (CNN) tailored Deep Learning Models, where we consider all possible 2D data such as Spectrogram, Mel-frequency Cepstral Coefficients (MFCC), spectral centroid, and spectral roll-off. In our experiments, using the publicly available respiratory sound database named ICBHI 2017 (5.5 hours of recordings containing 6898 respiratory cycles from 126 subjects), we received the highest performance with the area under the curve of 0.79 from Spectrogram as opposed to 0.48 AUC from the raw data from a pre-trained deep learning model: VGG16. Our study proved that 2D data representation could help better understand/analyze lung abnormalities as compared to 1D data. In addition, our results can be compared with previous works.
Keywords: Lung Abnormality· Respiratory Sound · 2D Data Representation · Deep Visual Features.