COVID-19 Detection from respiratory sounds with hierarchical spectrogram transformers

Simple item page
buir.contributor.authorAytekin, Ayçe İdil
buir.contributor.authorDalmaz, Onat
buir.contributor.authorGönç, Kaan
buir.contributor.authorSarıtaş, Emine Ülkü
buir.contributor.authorÇukur, Tolga
buir.contributor.orcidAytekin, Ayçe İdil|0009-0008-1849-4703
buir.contributor.orcidDalmaz, Onat|0000-0001-7978-5311
buir.contributor.orcidGönç, Kaan|0009-0009-4563-4369
buir.contributor.orcidSarıtaş, Emine Ülkü|0000-0001-8551-1077
buir.contributor.orcidÇukur, Tolga|0000-0002-2296-851X
dc.citation.epage1284en_US
dc.citation.issueNumber3
dc.citation.spage1273
dc.citation.volumeNumber28
dc.contributor.authorAytekin, Ayçe İdil
dc.contributor.authorDalmaz, Onat
dc.contributor.authorGönç, Kaan
dc.contributor.authorAnkishan, H.
dc.contributor.authorSarıtaş, Emine Ülkü
dc.contributor.authorBağcı, U.
dc.contributor.authorÇelik, H.
dc.contributor.authorÇukur, Tolga
dc.date.accessioned2024-03-15T13:18:24Z
dc.date.available2024-03-15T13:18:24Z
dc.date.issued2023-12-05
dc.departmentDepartment of Electrical and Electronics Engineering
dc.departmentNational Magnetic Resonance Research Center (UMRAM)
dc.departmentDepartment of Computer Engineering
dc.description.abstractMonitoring of prevalent airborne diseases such as COVID-19 characteristically involves respiratory assessments. While auscultation is a mainstream method for preliminary screening of disease symptoms, its util ity is hampered by the need for dedicated hospital visits. Remote monitoring based on recordings of respi ratory sounds on portable devices is a promising alter native, which can assist in early assessment of COVID-19 that primarily affects the lower respiratory tract. In this study, we introduce a novel deep learning approach to distinguish patients with COVID-19 from healthy controls given audio recordings of cough or breathing sounds. The proposed approach leverages a novel hierarchical spectro gram transformer (HST) on spectrogram representations of respiratory sounds. HST embodies self-attention mech anisms over local windows in spectrograms, and window size is progressively grown over model stages to capture local to global context. HST is compared against state-of the-art conventional and deep-learning baselines. Demon strations on crowd-sourced multi-national datasets indicate that HST outperforms competing methods, achieving over 90% area under the receiver operating characteristic curve (AUC) in detecting COVID-19 cases.
dc.identifier.doi10.1109/JBHI.2023.3339700
dc.identifier.eissn2168-2208
dc.identifier.issn2168-2194
dc.identifier.urihttps://hdl.handle.net/11693/114814
dc.language.isoEnglish
dc.publisherInstitute of Electrical and Electronics Engineers
dc.relation.isversionofhttps://dx.doi.org/10.1109/JBHI.2023.3339700
dc.source.titleIEEE Journal of Biomedical and Health Informatics
dc.subjectCOVID-19
dc.subjectRespiratory sound classification
dc.subjectAuditory
dc.subjectSpectrogram
dc.subjectTransformer
dc.subjectAuscultation
dc.titleCOVID-19 Detection from respiratory sounds with hierarchical spectrogram transformers
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
COVID-19_Detection_from_respiratory_sounds_with_hierarchical_spectrogram_transformers.pdf
Size:
7.3 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.01 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Department of Electrical and Electronics Engineering
Department of Computer Engineering
National Magnetic Resonance Research Center (UMRAM)