Abstract
Computed Tomography has become a vital screening method for the detection of coronavirus 2019 (COVID-19). With the high mortality rate and overload for domain experts, radiologists, and clinicians, there is a need for the application of a computerized diagnostic technique. To this effect, we have taken into consideration improving the performance of COVID-19 identification by tackling the issue of low quality and resolution of computed tomography images by introducing our method. We have reported about a technique named the modified enhanced super resolution generative adversarial network for a better high resolution of computed tomography images. Furthermore, in contrast to the fashion of increasing network depth and complexity to beef up imaging performance, we incorporated a Siamese capsule network that extracts distinct features for COVID-19 identification.The qualitative and quantitative results establish that the proposed model is effective, accurate, and robust for COVID-19 screening. We demonstrate the proposed model for COVID-19 identification on a publicly available dataset COVID-CT, which contains 349 COVID-19 and 463 non-COVID-19 computed tomography images. The proposed method achieves an accuracy of 97.92%, sensitivity of 98.85%, specificity of 97.21%, AUC of 98.03%, precision of 98.44%, and F1 score of 97.52%. Our approach obtained state-of-the-art performance, according to experimental results, which is helpful for COVID-19 screening. This new conceptual framework is proposed to play an influential task in the issue facing COVID-19 and related ailments, with the availability of few datasets.
Highlights
IntroductionWuhan city of Hubei province in China is the ground-zero of the epidemic where COVID-19 was first discovered in December 2019, and has since escalated around the world, resulting in the ongoing coronavirus pandemic of 2021
In investigating the performance of our proposed architecture on COVID-19 screening diagnosis, we sorted for an open domain dataset of CT images called the COVID-CT dataset
In avoiding over-fitting and enabling our dataset to train well, we balanced our dataset by selecting only 349 cases from each class.With the total of 698 images, 298 images were taken as a test set and 400 images for training, of which 400 images were paired with 10 distinct images, which amounted to 4000 images, 3000 images for the training set and 1000 images for the validation set
Summary
Wuhan city of Hubei province in China is the ground-zero of the epidemic where COVID-19 was first discovered in December 2019, and has since escalated around the world, resulting in the ongoing coronavirus pandemic of 2021. The reverse transcription polymerase chain reaction, RT-PCR, being an accepted procedure for diagnosing COVID-19, is manually done to perform a viral nucleic acid test by using nasopharyngeal and throat swabs seen to be affected by sampling errors and low viral load. RT-PCR [3] is complex and time consuming, and it requires multiple tests for a definitive result and relatively low sensitivity. There are insufficient test-kits and domain professionals in the clinics, and a swift increase in the value of infected patients demand for an automatic screening application, which serves as an alternative method for medical professionals to hastily identify the infected patients who need instant isolation and additional clinical verification. Alternative screening methods [4,5,6] have been established for the COVID-19 identification, which employs chest X-ray or computed tomography [7]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
