Abstract
COVID-19 is a pandemic outbreak that has slaughtered millions worldwide and infected millions more. RT-PCR examination, CT (Computed Tomography) scans, and Chest X-ray (CXR) images are used to diagnose it. Most medical centers lack CT scanners and RT-PCR (Reverse Transcription Polymerase Chain Reaction) testing, as a result, in many circumstances, X-rays of the chest have become the most time and cost-effective technique for supporting clinicians in decision-making. Any technological process that aids in the fast diagnosis of COVID-19 infection can be highly beneficial to health care providers. A diagnosis recommender device that will aid the doctor in examining the patient's lung scans would reduce the doctor's medical workload. When compared to machine learning techniques, deep learning approaches have shown unbeatable results in categorizing the realm of medical imaging. However, currently available databases do not create such schemes because they are extremely diverse and skewed against extreme cases. This research paper used a VGG-16 architecture which was already pre-trained on the ImageNet dataset to predict COVID-19, non COVID-19 and pneumonia patients from chest X-ray images. The employed VGG-16 architecture, is one of the CNN architectures, used for image classification. Classical data augmentation techniques were used to increase the size of dataset. VGG-16 model has predicted COVID-19, non COVID-19 and Pneumonia patients from chest X-ray images with a 92.5% accuracy using the transfer learning.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.