An End-to-End Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise

<p dir="ltr">The heart sound signals captured via a digital stethoscope are often distorted by environmental and physiological noise, altering their salient and critical properties. The problem is exacerbated in crowded low-resource hospital settings with high noise levels which degr...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Shams Nafisa Ali (17949191) (author)
مؤلفون آخرون: Samiul Based Shuvo (17949194) (author), Muhammad Ishtiaque Sayeed Al-Manzo (17949197) (author), Anwarul Hasan (1332066) (author), Taufiq Hasan (17949200) (author)
منشور في: 2023
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513527490805760
author Shams Nafisa Ali (17949191)
author2 Samiul Based Shuvo (17949194)
Muhammad Ishtiaque Sayeed Al-Manzo (17949197)
Anwarul Hasan (1332066)
Taufiq Hasan (17949200)
author2_role author
author
author
author
author_facet Shams Nafisa Ali (17949191)
Samiul Based Shuvo (17949194)
Muhammad Ishtiaque Sayeed Al-Manzo (17949197)
Anwarul Hasan (1332066)
Taufiq Hasan (17949200)
author_role author
dc.creator.none.fl_str_mv Shams Nafisa Ali (17949191)
Samiul Based Shuvo (17949194)
Muhammad Ishtiaque Sayeed Al-Manzo (17949197)
Anwarul Hasan (1332066)
Taufiq Hasan (17949200)
dc.date.none.fl_str_mv 2023-07-05T06:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2023.3292551
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/An_End-to-End_Deep_Learning_Framework_for_Real-Time_Denoising_of_Heart_Sounds_for_Cardiac_Disease_Detection_in_Unseen_Noise/25205231
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electrical engineering
Electronics, sensors and digital hardware
Materials engineering
Noise reduction
Heart
Phonocardiography
Noise measurement
Hospitals
Lungs
Electrocardiography
Deep learning
Cardiovascular diseases
Cardiac disease
Heart sound
real time denoising
denoising autoencoder
dc.title.none.fl_str_mv An End-to-End Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">The heart sound signals captured via a digital stethoscope are often distorted by environmental and physiological noise, altering their salient and critical properties. The problem is exacerbated in crowded low-resource hospital settings with high noise levels which degrades the diagnostic performance. In this study, we present a novel deep encoder-decoder-based denoising architecture (LU-Net) to suppress ambient and internal lung sound noises. Training is done using a large benchmark PCG dataset mixed with physiological noise, i.e., breathing sounds. Two different noisy datasets were prepared for experimental evaluation by mixing unseen lung sounds and hospital ambient noises with the clean heart sound recordings. We also used the inherently noisy portion of the PASCAL heart sound dataset for evaluation. The proposed framework showed effective suppression of background noises in both unseen real-world data and synthetically generated noisy heart sound recordings, improving the signal-to-noise ratio (SNR) level by 5.575 dB on an average using only 1.32 M parameters. The proposed model outperforms the current state-of-the-art U-Net model with an average SNR improvement of 5.613 dB and 5.537 dB in the presence of lung sound and unseen hospital noise, respectively. LU-Net also outperformed the state-of-the-art Fully Convolutional Network (FCN) by 1.750 dB and 1.748 dB for lung sound and unseen hospital noise conditions, respectively. In addition, the proposed denoising method model improves classification accuracy by 38.93% in the noisy portion of the PASCAL heart sound dataset. The results presented in the paper indicate that our proposed architecture demonstrated a robust denoising performance on different datasets with diverse levels and characteristics of noise. The proposed deep learning-based PCG denoising approach is a pioneering study that can significantly improve the accuracy of computer-aided auscultation systems for detecting cardiac diseases in noisy, low-resource hospitals and underserved communities. </p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="http://creativecommons.org/licenses/by/4.0" target="_blank">http://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2023.3292551" target="_blank">https://dx.doi.org/10.1109/access.2023.3292551</a></p>
eu_rights_str_mv openAccess
id Manara2_c075d04ee4faa3445d8c593524365be7
identifier_str_mv 10.1109/access.2023.3292551
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25205231
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling An End-to-End Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen NoiseShams Nafisa Ali (17949191)Samiul Based Shuvo (17949194)Muhammad Ishtiaque Sayeed Al-Manzo (17949197)Anwarul Hasan (1332066)Taufiq Hasan (17949200)EngineeringElectrical engineeringElectronics, sensors and digital hardwareMaterials engineeringNoise reductionHeartPhonocardiographyNoise measurementHospitalsLungsElectrocardiographyDeep learningCardiovascular diseasesCardiac diseaseHeart soundreal time denoisingdenoising autoencoder<p dir="ltr">The heart sound signals captured via a digital stethoscope are often distorted by environmental and physiological noise, altering their salient and critical properties. The problem is exacerbated in crowded low-resource hospital settings with high noise levels which degrades the diagnostic performance. In this study, we present a novel deep encoder-decoder-based denoising architecture (LU-Net) to suppress ambient and internal lung sound noises. Training is done using a large benchmark PCG dataset mixed with physiological noise, i.e., breathing sounds. Two different noisy datasets were prepared for experimental evaluation by mixing unseen lung sounds and hospital ambient noises with the clean heart sound recordings. We also used the inherently noisy portion of the PASCAL heart sound dataset for evaluation. The proposed framework showed effective suppression of background noises in both unseen real-world data and synthetically generated noisy heart sound recordings, improving the signal-to-noise ratio (SNR) level by 5.575 dB on an average using only 1.32 M parameters. The proposed model outperforms the current state-of-the-art U-Net model with an average SNR improvement of 5.613 dB and 5.537 dB in the presence of lung sound and unseen hospital noise, respectively. LU-Net also outperformed the state-of-the-art Fully Convolutional Network (FCN) by 1.750 dB and 1.748 dB for lung sound and unseen hospital noise conditions, respectively. In addition, the proposed denoising method model improves classification accuracy by 38.93% in the noisy portion of the PASCAL heart sound dataset. The results presented in the paper indicate that our proposed architecture demonstrated a robust denoising performance on different datasets with diverse levels and characteristics of noise. The proposed deep learning-based PCG denoising approach is a pioneering study that can significantly improve the accuracy of computer-aided auscultation systems for detecting cardiac diseases in noisy, low-resource hospitals and underserved communities. </p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="http://creativecommons.org/licenses/by/4.0" target="_blank">http://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2023.3292551" target="_blank">https://dx.doi.org/10.1109/access.2023.3292551</a></p>2023-07-05T06:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2023.3292551https://figshare.com/articles/journal_contribution/An_End-to-End_Deep_Learning_Framework_for_Real-Time_Denoising_of_Heart_Sounds_for_Cardiac_Disease_Detection_in_Unseen_Noise/25205231CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/252052312023-07-05T06:00:00Z
spellingShingle An End-to-End Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise
Shams Nafisa Ali (17949191)
Engineering
Electrical engineering
Electronics, sensors and digital hardware
Materials engineering
Noise reduction
Heart
Phonocardiography
Noise measurement
Hospitals
Lungs
Electrocardiography
Deep learning
Cardiovascular diseases
Cardiac disease
Heart sound
real time denoising
denoising autoencoder
status_str publishedVersion
title An End-to-End Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise
title_full An End-to-End Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise
title_fullStr An End-to-End Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise
title_full_unstemmed An End-to-End Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise
title_short An End-to-End Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise
title_sort An End-to-End Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise
topic Engineering
Electrical engineering
Electronics, sensors and digital hardware
Materials engineering
Noise reduction
Heart
Phonocardiography
Noise measurement
Hospitals
Lungs
Electrocardiography
Deep learning
Cardiovascular diseases
Cardiac disease
Heart sound
real time denoising
denoising autoencoder