Home > Research > Publications & Outputs > Proposing a novel deep network for detecting CO...

Links

Text available via DOI:

View graph of relations

Proposing a novel deep network for detecting COVID-19 based on chest images

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Proposing a novel deep network for detecting COVID-19 based on chest images. / Dialameh, M.; Hamzeh, A.; Rahmani, H. et al.
In: Scientific Reports, Vol. 12, No. 1, 3116, 24.02.2022.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Dialameh, M, Hamzeh, A, Rahmani, H, Radmard, AR & Dialameh, S 2022, 'Proposing a novel deep network for detecting COVID-19 based on chest images', Scientific Reports, vol. 12, no. 1, 3116. https://doi.org/10.1038/s41598-022-06802-7

APA

Dialameh, M., Hamzeh, A., Rahmani, H., Radmard, A. R., & Dialameh, S. (2022). Proposing a novel deep network for detecting COVID-19 based on chest images. Scientific Reports, 12(1), Article 3116. https://doi.org/10.1038/s41598-022-06802-7

Vancouver

Dialameh M, Hamzeh A, Rahmani H, Radmard AR, Dialameh S. Proposing a novel deep network for detecting COVID-19 based on chest images. Scientific Reports. 2022 Feb 24;12(1):3116. doi: 10.1038/s41598-022-06802-7

Author

Dialameh, M. ; Hamzeh, A. ; Rahmani, H. et al. / Proposing a novel deep network for detecting COVID-19 based on chest images. In: Scientific Reports. 2022 ; Vol. 12, No. 1.

Bibtex

@article{f437262b9a6e486d8eaf69c3c9163227,
title = "Proposing a novel deep network for detecting COVID-19 based on chest images",
abstract = "The rapid outbreak of coronavirus threatens humans{\textquoteright} life all around the world. Due to the insufficient diagnostic infrastructures, developing an accurate, efficient, inexpensive, and quick diagnostic tool is of great importance. To date, researchers have proposed several detection models based on chest imaging analysis, primarily based on deep neural networks; however, none of which could achieve a reliable and highly sensitive performance yet. Therefore, the nature of this study is primary epidemiological research that aims to overcome the limitations mentioned above by proposing a large-scale publicly available dataset of chest computed tomography scan (CT-scan) images consisting of more than 13k samples. Secondly, we propose a more sensitive deep neural networks model for CT-scan images of the lungs, providing a pixel-wise attention layer on top of the high-level features extracted from the network. Moreover, the proposed model is extended through a transfer learning approach for being applicable in the case of chest X-Ray (CXR) images. The proposed model and its extension have been trained and evaluated through several experiments. The inclusion criteria were patients with suspected PE and positive real-time reverse-transcription polymerase chain reaction (RT-PCR) for SARS-CoV-2. The exclusion criteria were negative or inconclusive RT-PCR and other chest CT indications. Our model achieves an AUC score of 0.886, significantly better than its closest competitor, whose AUC is 0.843. Moreover, the obtained results on another commonly-used benchmark show an AUC of 0.899, outperforming related models. Additionally, the sensitivity of our model is 0.858, while that of its closest competitor is 0.81, explaining the efficiency of pixel-wise attention strategy in detecting coronavirus. Our promising results and the efficiency of the models imply that the proposed models can be considered reliable tools for assisting doctors in detecting coronavirus. ",
author = "M. Dialameh and A. Hamzeh and H. Rahmani and A.R. Radmard and S. Dialameh",
year = "2022",
month = feb,
day = "24",
doi = "10.1038/s41598-022-06802-7",
language = "English",
volume = "12",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

RIS

TY - JOUR

T1 - Proposing a novel deep network for detecting COVID-19 based on chest images

AU - Dialameh, M.

AU - Hamzeh, A.

AU - Rahmani, H.

AU - Radmard, A.R.

AU - Dialameh, S.

PY - 2022/2/24

Y1 - 2022/2/24

N2 - The rapid outbreak of coronavirus threatens humans’ life all around the world. Due to the insufficient diagnostic infrastructures, developing an accurate, efficient, inexpensive, and quick diagnostic tool is of great importance. To date, researchers have proposed several detection models based on chest imaging analysis, primarily based on deep neural networks; however, none of which could achieve a reliable and highly sensitive performance yet. Therefore, the nature of this study is primary epidemiological research that aims to overcome the limitations mentioned above by proposing a large-scale publicly available dataset of chest computed tomography scan (CT-scan) images consisting of more than 13k samples. Secondly, we propose a more sensitive deep neural networks model for CT-scan images of the lungs, providing a pixel-wise attention layer on top of the high-level features extracted from the network. Moreover, the proposed model is extended through a transfer learning approach for being applicable in the case of chest X-Ray (CXR) images. The proposed model and its extension have been trained and evaluated through several experiments. The inclusion criteria were patients with suspected PE and positive real-time reverse-transcription polymerase chain reaction (RT-PCR) for SARS-CoV-2. The exclusion criteria were negative or inconclusive RT-PCR and other chest CT indications. Our model achieves an AUC score of 0.886, significantly better than its closest competitor, whose AUC is 0.843. Moreover, the obtained results on another commonly-used benchmark show an AUC of 0.899, outperforming related models. Additionally, the sensitivity of our model is 0.858, while that of its closest competitor is 0.81, explaining the efficiency of pixel-wise attention strategy in detecting coronavirus. Our promising results and the efficiency of the models imply that the proposed models can be considered reliable tools for assisting doctors in detecting coronavirus.

AB - The rapid outbreak of coronavirus threatens humans’ life all around the world. Due to the insufficient diagnostic infrastructures, developing an accurate, efficient, inexpensive, and quick diagnostic tool is of great importance. To date, researchers have proposed several detection models based on chest imaging analysis, primarily based on deep neural networks; however, none of which could achieve a reliable and highly sensitive performance yet. Therefore, the nature of this study is primary epidemiological research that aims to overcome the limitations mentioned above by proposing a large-scale publicly available dataset of chest computed tomography scan (CT-scan) images consisting of more than 13k samples. Secondly, we propose a more sensitive deep neural networks model for CT-scan images of the lungs, providing a pixel-wise attention layer on top of the high-level features extracted from the network. Moreover, the proposed model is extended through a transfer learning approach for being applicable in the case of chest X-Ray (CXR) images. The proposed model and its extension have been trained and evaluated through several experiments. The inclusion criteria were patients with suspected PE and positive real-time reverse-transcription polymerase chain reaction (RT-PCR) for SARS-CoV-2. The exclusion criteria were negative or inconclusive RT-PCR and other chest CT indications. Our model achieves an AUC score of 0.886, significantly better than its closest competitor, whose AUC is 0.843. Moreover, the obtained results on another commonly-used benchmark show an AUC of 0.899, outperforming related models. Additionally, the sensitivity of our model is 0.858, while that of its closest competitor is 0.81, explaining the efficiency of pixel-wise attention strategy in detecting coronavirus. Our promising results and the efficiency of the models imply that the proposed models can be considered reliable tools for assisting doctors in detecting coronavirus.

U2 - 10.1038/s41598-022-06802-7

DO - 10.1038/s41598-022-06802-7

M3 - Journal article

VL - 12

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 3116

ER -