RespireNet: A Deep Neural Network for Accurately Detecting Abnormal Lung Sounds in Limited Data Setting

Gairola, Siddhartha; Tom, Francis; Kwatra, Nipun; Jain, Mohit

doi:10.1109/embc46164.2021.9630091

Cited by 64 publications

(39 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We observe a different frequency response across recording stethoscopes which results in a performance degradation for under-represented devices. Hence, we calibrate the features of the audio segments by applying spectrum correction instead of training or fine-tuning the model for a specific device [32], [33]. The spectrum correction or calibration was first applied for acoustic scene classification [31].…”

Section: B Spectrum Correctionmentioning

confidence: 99%

“…al. [33] proposed a RespireNet model based on ResNet34 and fully connected layers with a set of techniques i.e. device specific fine-tuning, concatenationbased augmentation, blank region clipping and smart padding to improve the accuracy.…”

Section: A Lung Sound Classification On Icbhi Datasetmentioning

confidence: 99%

“…Currently, there are a few approaches which address this problem. They focus on either training or finetuning specific models for a specific device which is used for majority recordings to limit sensitivity to characteristics of the recording device [32], [33].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Lung Sound Classification Using Co-Tuning and Stochastic Normalization

Nguyen

Pernkopf

2022

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Computational methods for lung sound analysis are beneficial for computer-aided diagnosis support, storage and monitoring in critical care. In this paper, we use pre-trained ResNet models as backbone architectures for classification of adventitious lung sounds and respiratory diseases. The learned representation of the pre-trained model is transferred by using vanilla fine-tuning, co-tuning, stochastic normalization and the combination of the co-tuning and stochastic normalization techniques. Furthermore, data augmentation in both time domain and time-frequency domain is used to account for the class imbalance of the ICBHI and our multi-channel lung sound dataset. Additionally, we introduce spectrum correction to account for the variations of the recording device properties on the ICBHI dataset. Empirically, our proposed systems mostly outperform all state-of-the-art lung sound classification systems for the adventitious lung sounds and respiratory diseases of both datasets.

show abstract

Section: B Spectrum Correctionmentioning

confidence: 99%

Section: A Lung Sound Classification On Icbhi Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Lung Sound Classification Using Co-Tuning and Stochastic Normalization

Nguyen

Pernkopf

2022

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…This technique was easily incorporated with the diagnostic tools for achieving effective results, and also offered detailed analysis with respect to the left and right lungs, but the computational cost was high in this method. Siddhartha Gairolaet al [8] introduced a Deep Neural Network (DNN) for finding the anomalous lung sounds accurately. This approach was easily incorporated with other frameworks to minimize the computational complexities.However, this model failed to utilize larger datasets in order to achieve effective results.…”

Section: Literature Surveymentioning

confidence: 99%

Spectral features and optimal Hierarchical attention networks for pulmonary abnormality detection from the respiratory sound signals

Dar¹,

Srivastava²,

Lone

2022

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

“…Recently, with coronavirus disease spreading the situation has become extremely serious. Thus, early detection of infected people is very vital in limiting the spread of respiratory diseases and COVID-19 [3]. The fundamental methods employed for diagnosing COVID-19 and respiratory diseases are computerized tomography (CT), chest X-rays, pulmonary function testing [1], [4].…”

Section: Introductionmentioning

confidence: 99%

Employing deep learning for lung sounds classification

Satea¹,

Elameer²,

Salman³

et al. 2022

IJECE

View full text Add to dashboard Cite

Respiratory diseases indicate severe medical problems. They cause death for more than three million people annually according to the world health organization (WHO). Recently, with corona virus disease 19 (COVID-19) spreading the situation has become extremely serious. Thus, early detection of infected people is very vital in limiting the spread of respiratory diseases and COVID-19. In this paper, we have examined two different models using convolution neural networks. Firstly, we proposed and build a convolution neural network (CNN) model from scratch for classification the lung breath sounds. Secondly, we employed transfer learning using the pre-trained network AlexNet applying on the similar dataset. Our proposed model achieved an accuracy of 0.91 whereas the transfer learning model performing much better with an accuracy of 0.94.

show abstract

RespireNet: A Deep Neural Network for Accurately Detecting Abnormal Lung Sounds in Limited Data Setting

Cited by 64 publications

References 22 publications

Lung Sound Classification Using Co-Tuning and Stochastic Normalization

Lung Sound Classification Using Co-Tuning and Stochastic Normalization

Spectral features and optimal Hierarchical attention networks for pulmonary abnormality detection from the respiratory sound signals

Employing deep learning for lung sounds classification

Contact Info

Product

Resources

About