Home > Research > Publications & Outputs > Towards Robust Diagnosis of COVID-19 using Visi...

Electronic data

Links

Text available via DOI:

View graph of relations

Towards Robust Diagnosis of COVID-19 using Vision Self-attention Transformer

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Towards Robust Diagnosis of COVID-19 using Vision Self-attention Transformer. / Mehboob, Fozia; Rauf, Abdul; Jiang, Richard et al.

In: Scientific Reports, Vol. 12, 8922, 26.05.2022.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Mehboob, F, Rauf, A, Jiang, R, Saudagar, AKJ, Malik, KM, Khan, MB, Hasnat, MHA, AlTameem, A & AlKhathami, M 2022, 'Towards Robust Diagnosis of COVID-19 using Vision Self-attention Transformer', Scientific Reports, vol. 12, 8922. https://doi.org/10.1038/s41598-022-13039-x

APA

Mehboob, F., Rauf, A., Jiang, R., Saudagar, A. K. J., Malik, K. M., Khan, M. B., Hasnat, M. H. A., AlTameem, A., & AlKhathami, M. (2022). Towards Robust Diagnosis of COVID-19 using Vision Self-attention Transformer. Scientific Reports, 12, [8922]. https://doi.org/10.1038/s41598-022-13039-x

Vancouver

Mehboob F, Rauf A, Jiang R, Saudagar AKJ, Malik KM, Khan MB et al. Towards Robust Diagnosis of COVID-19 using Vision Self-attention Transformer. Scientific Reports. 2022 May 26;12:8922. doi: 10.1038/s41598-022-13039-x

Author

Mehboob, Fozia ; Rauf, Abdul ; Jiang, Richard et al. / Towards Robust Diagnosis of COVID-19 using Vision Self-attention Transformer. In: Scientific Reports. 2022 ; Vol. 12.

Bibtex

@article{a9d6bc6a0cfd4e46b03ceb831228d4fc,
title = "Towards Robust Diagnosis of COVID-19 using Vision Self-attention Transformer",
abstract = "The outbreak of COVID-19, since its appearance, has affected about 200 countries and endangered millions of lives. COVID-19 is extremely contagious disease, and it can quickly incapacitate the healthcare systems if infected cases are not handled timely. Several Conventional Neural Networks (CNN) based techniques have been developed to diagnose the COVID-19. These techniques require a large, labelled dataset to train the algorithm fully, but there are not too many labelled datasets. To mitigate this problem and facilitate the diagnosis of COVID-19, we developed a self-attention transformer-based approach having self-attention mechanism using CT slices. The architecture of transformer can exploit the ample unlabelled datasets using pre-training. The paper aims to compare the performances of self-attention transformer-based approach with CNN and Ensemble classifiers for diagnosis of COVID-19 using binary Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection and multi-class Hybrid-learning for UnbiaSed predicTion of COVID-19 (HUST-19) CT scan dataset. To perform this comparison, we have tested Deep learning-based classifiers and ensemble classifiers with proposed approach using CT scan images. Proposed approach is more effective in detection of COVID-19 with an accuracy of 99.7% on multi-class HUST-19, whereas 98% on binary class SARS-CoV-2 dataset. Cross corpus evaluation achieves accuracy of 93% by training the model with Hust19 dataset and testing using Brazilian COVID dataset",
author = "Fozia Mehboob and Abdul Rauf and Richard Jiang and A.K.J. Saudagar and Malik, {Khalid Mahmood} and Khan, {Muhammad Badruddin} and Hasnat, {Mozaherul Hoque Abdul} and Abdullah AlTameem and Mohammed AlKhathami",
year = "2022",
month = may,
day = "26",
doi = "10.1038/s41598-022-13039-x",
language = "English",
volume = "12",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",

}

RIS

TY - JOUR

T1 - Towards Robust Diagnosis of COVID-19 using Vision Self-attention Transformer

AU - Mehboob, Fozia

AU - Rauf, Abdul

AU - Jiang, Richard

AU - Saudagar, A.K.J.

AU - Malik, Khalid Mahmood

AU - Khan, Muhammad Badruddin

AU - Hasnat, Mozaherul Hoque Abdul

AU - AlTameem, Abdullah

AU - AlKhathami, Mohammed

PY - 2022/5/26

Y1 - 2022/5/26

N2 - The outbreak of COVID-19, since its appearance, has affected about 200 countries and endangered millions of lives. COVID-19 is extremely contagious disease, and it can quickly incapacitate the healthcare systems if infected cases are not handled timely. Several Conventional Neural Networks (CNN) based techniques have been developed to diagnose the COVID-19. These techniques require a large, labelled dataset to train the algorithm fully, but there are not too many labelled datasets. To mitigate this problem and facilitate the diagnosis of COVID-19, we developed a self-attention transformer-based approach having self-attention mechanism using CT slices. The architecture of transformer can exploit the ample unlabelled datasets using pre-training. The paper aims to compare the performances of self-attention transformer-based approach with CNN and Ensemble classifiers for diagnosis of COVID-19 using binary Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection and multi-class Hybrid-learning for UnbiaSed predicTion of COVID-19 (HUST-19) CT scan dataset. To perform this comparison, we have tested Deep learning-based classifiers and ensemble classifiers with proposed approach using CT scan images. Proposed approach is more effective in detection of COVID-19 with an accuracy of 99.7% on multi-class HUST-19, whereas 98% on binary class SARS-CoV-2 dataset. Cross corpus evaluation achieves accuracy of 93% by training the model with Hust19 dataset and testing using Brazilian COVID dataset

AB - The outbreak of COVID-19, since its appearance, has affected about 200 countries and endangered millions of lives. COVID-19 is extremely contagious disease, and it can quickly incapacitate the healthcare systems if infected cases are not handled timely. Several Conventional Neural Networks (CNN) based techniques have been developed to diagnose the COVID-19. These techniques require a large, labelled dataset to train the algorithm fully, but there are not too many labelled datasets. To mitigate this problem and facilitate the diagnosis of COVID-19, we developed a self-attention transformer-based approach having self-attention mechanism using CT slices. The architecture of transformer can exploit the ample unlabelled datasets using pre-training. The paper aims to compare the performances of self-attention transformer-based approach with CNN and Ensemble classifiers for diagnosis of COVID-19 using binary Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection and multi-class Hybrid-learning for UnbiaSed predicTion of COVID-19 (HUST-19) CT scan dataset. To perform this comparison, we have tested Deep learning-based classifiers and ensemble classifiers with proposed approach using CT scan images. Proposed approach is more effective in detection of COVID-19 with an accuracy of 99.7% on multi-class HUST-19, whereas 98% on binary class SARS-CoV-2 dataset. Cross corpus evaluation achieves accuracy of 93% by training the model with Hust19 dataset and testing using Brazilian COVID dataset

U2 - 10.1038/s41598-022-13039-x

DO - 10.1038/s41598-022-13039-x

M3 - Journal article

VL - 12

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 8922

ER -