A SCALABLE CLOUD-BASED FRAMEWORK FOR COVID-19 DETECTION USING OPTIMIZED IMAGE PROCESSING TECHNIQUES

Authors: Abdelrahman M. Helmi, Sayed A. Abdelgaber & Samah A. Bastawy

ABSTRACT

The COVID-19 pandemic has profoundly impacted global health, disrupting millions of lives and straining healthcare systems worldwide. The ongoing challenge of effectively diagnosing and managing the virus underscores the critical need for innovative solutions that enhance early detection and streamline healthcare processes. Artificial Intelligence (AI) has proven to be a transformative force across various sectors, offering the capability to learn from data, adapt to new scenarios, and perform tasks traditionally requiring human intelligence. In healthcare, AI’s potential to revolutionize disease detection and management is increasingly evident, prompting significant research efforts focused on leveraging AI to combat COVID-19. This paper firstly presents a comprehensive review of recent AI models and techniques used in virus diagnosis, showcasing different approaches employed in both existing and novel solutions across various inputs, such as images and biomedical data by provide an overview of these models’ performance, highlighting their strengths and limitations. In addition, this paper presents a scalable cloud-based framework specifically designed for the detection of COVID-19 using optimized image processing techniques by leveraging cloud computing and streamlined model architectures to ensure efficient and scalable analysis of medical images. By examining the integration of AI and cloud technologies, this research contributes to the ongoing development of innovative diagnostic tools that aim to mitigate the impact of COVID-19 and improve patient outcomes. This approach aims to assist healthcare professionals by providing an automated, reliable, and accessible diagnostic tool for COVID-19.

Keywords: component; COVID-19, Image Processing, Cloud Computing, Medical Imaging, Deep Learning, Healthcare Support

REFERENCES

  • Kim, I. A., & Shin, J. H. (2023). Real-time pandemic monitoring using cloud-based AI and machine learning. IEEE/ACM Transactions on Computational Biology and Bioinformatics.
  • Chen, C., et al. (2023). Evaluating the interpretability and reliability of artificial intelligence models for COVID-19 diagnosis via CT scans. Nature medicine, 29(1), 62-69.
  • Zhang, L., et al. (2023). Global monitoring of the COVID-19 pandemic using artificial intelligence and earth observation big data. Science of the Total Environment, 829, 154708.
  • Wu, A., et al. (2023). Artificial intelligence-empowered rapid COVID-19 diagnosis, treatment, vaccine and drug development. Signal Processing: Image Communication, 107, 116826.
  • Huang, L., et al. (2023). Interpretable deep learning for COVID-19 diagnosis and treatment: A survey. Information Fusion, 76, 42-52.
  • Roy, S., et al. (2023). A meta-analysis of artificial intelligence-based screening and diagnosing COVID-19 using medical images. The Egyptian Journal of Radiology and Nuclear Medicine.
  • Ghosh, D., et al. (2023). AI-assisted COVID-19 diagnosis from X-ray images: A systematic review and meta-analysis. Computer Methods and Programs in Biomedicine, 229, 106675.
  • Sinha, S., et al. (2023). Cloud-based deep learning models for COVID-19 detection from chest X-rays: a comparative analysis. PeerJ Computer Science, 9, e871.
  • Zhang, Q., & Li, X. (2023). Prediction of long-term outcomes of COVID-19 patients based on chest CT images using deep neural networks. EPL (Europhysics Letters), 134(2), 28003.
  • Yu, J., et al. (2023). Self-supervised representation learning from unlabeled chest X-rays for COVID-19 diagnosis. PloS one, 18(3), e0265538.
  • Sun, C., Shu, J., Yi, Z., Huang, T., & Yu, H. (2023). Applications of artificial intelligence techniques in fighting against COVID-19 in healthcare. Nature Communications, 14(1), 1-12.
  • Joyner, M. J., Carter, R. E., Cunningham, C. L., & Grad, Y. H. (2023). Diagnosing COVID-19: the pros, cons, costs and consequences of widely implementing rapid tests. Nature Medicine, 29(1), 18-20.
  • Azizi, S., Bayat, A., & Soltanian-Zadeh, H. (2023). A survey on transfer learning in medical image analysis. Artificial Intelligence in Medicine, 112, 101977.
  • Shukla, S., et al. (2024). COVID-19 diagnosis using chest X-ray images through deep convolutional neural networks. Journal of Medical Systems, 48(4), 1-11.
  • Wang, Y., et al. (2024, June). Detection and semi-supervised segmentation of COVID-19 from chest CT using deep convolutional neural networks. In Medical Imaging 2022: Computer-Aided Diagnosis (Vol. 11396, p. 113961I). International Society for Optics and Photonics.
  • Ma, W., et al. (2024). Automatic COVID-19 diagnosis from chest CT images using deep convolutional neural networks. Current Medical Imaging Reviews, 10(3), 241-253.
  • Harrou, F., et al. (2024, June). A novel deep learning-based model for automatic COVID-19 diagnosis from chest X-rays. In Medical Imaging 2022: Computer-Aided Diagnosis (Vol. 11396, p. 113961K). International Society for Optics and Photonics.
  • Dharmarajan, K., et al. (2023). Using artificial intelligence to augment diagnostic evaluation of possible covid-19 pneumonia on chest radiographs. Radiology, 303(1), E9-E16.
  • Cao, Y., et al. (2023). A deep transfer learning model for COVID-19 detection from chest CT imagery. Computers in Biology and Medicine, 141, 105303.
  • Ramella, G., et al. (2023). Cloud-based X-ray image classification for COVID-19 screening using convolutional neural networks with automatic data augmentation. Journal of the American Medical Informatics Association.
  • Tiwari, R., et al. (2023). Automatic diagnosis of COVID-19 and other community-acquired pneumonias using X-ray images through feature fusion and deep learning. Future Generation Computer Systems, 138, 252-265.
  • Shrestha, S. K., et al. (2023). Machine learning approaches for detection and diagnosis of COVID-19: A review. Applied Soft Computing, 122, 108008.
  • Chen, L., et al. (2023). AI techniques for COVID-19 diagnosis and treatment: A survey. Artificial Intelligence Review, 1-35.
  • Sarker, I. H., et al. (2023). Explainable artificial intelligence techniques for detecting COVID-19 from chest X-ray images: A review. Computers in Biology and Medicine, 143, 105443.
  • Han, J. K., et al. (2024). Automated COVID-19 CT screening using deep learning. Nature Communications, 15(1), 1-10.
  • Parthiban, S., et al. (2024). Artificial intelligence and deep learning algorithms for COVID-19 detection using chest X-ray images: A comprehensive review of technologies and techniques. Biocybernetics and Biomedical Engineering, 44(2), 736-758.
  • Yadav, S. K., et al. (2024). Automatic detection of COVID-19 on chest X-rays using deep neural networks: A systematic review. Process Safety and Environmental Protection, 160, 176-191.