Back to the list
Congress: ECR25
Poster Number: C-11189
Type: Poster: EPOS Radiologist (scientific)
Authorblock: M. M. Masoomi1, L. A. Al Kandari2, H. R. E. Elziat2, A. Mohammad2, T. Shaker3; 1Portsmouth/UK, 2KUWAIT/KW, 3Cairo/EG
Disclosures:
Michael Michael Masoomi: Nothing to disclose
Latifa Abdullah Al Kandari: Nothing to disclose
Haytham Ramzy Elsayed Elziat: Nothing to disclose
Amr Mohammad: Nothing to disclose
Taha Shaker: Nothing to disclose
Keywords: Artificial Intelligence, Emergency, Lung, Conventional radiography, Digital radiography, Computer Applications-Detection, diagnosis, Screening, Chronic obstructive airways disease, Education and training, Infection
Purpose OBJECTIVESThe primary objective of this study is to propose, develop, and assess an automated technique for detecting COVID-19, viral pneumonia, and normal lung conditions from digital chest X-ray (CXR) images. Furthermore, the study aims to apply pre-trained deep learning algorithms to enhance detection accuracy, ensuring the reliable and efficient classification of these conditions based on the structural differences observed in the chest X-ray images.
Read more Methods and materials METHODSDatasetsThe dataset used in this study was sourced from Kaggle (https://www.kaggle.com/code/mob2dr/98-7-covid-pneumonia-normal-using-xception/data) following a recent revision. After filtration, the final dataset consists of 8,470 Chest X-ray (CXR) images, categorized into three labels: COVID-19, Viral Pneumonia, and Normal (see Table 1). The input images from the dataset were initially converted into matrix format, and the matrices were labeled based on the relative differences observed in the images. The model learns to recognize these differences during the training phase and uses this information...
Read more Results RESULTS We are witnessing a significant transformation in global healthcare. Fueled by data and analytics, a range of new technologies and treatments—from advanced therapies to artificial intelligence (AI)—is reshaping how we diagnose and treat patients. The healthcare industry in Kuwait is entering the era of digital innovation, with both public and private sectors investing heavily in their digital transformation. The results from this study highlight the substantial potential of the proposed deep learning techniques, particularly Convolutional Neural Networks (CNNs), in...
Read more Conclusion CONCLUSIONSFrom a clinical perspective, the ability to rapidly and accurately classify and diagnose lung infections will lead to improved patient outcomes, faster diagnoses, and more efficient use of resources. By automating this process, healthcare providers can focus on more complex clinical tasks and decision-making, while AI offers a scalable solution for enhancing diagnostic accuracy. The developed method reduces human error by assisting healthcare professionals in making more precise and timely diagnoses. ACKNOWLEDGMENTThis project was supported by the grant [CN23-13NR-2059] from the...
Read more References  REFERENCES Smith, J. R., Mason, D. E., & Cummings, J. (2020). The role of chest X-ray in diagnosing pneumonia and COVID-19. Radiology Today, 41(5), 23-27. Lee, C. H., Ho, M. L., & Wang, H. P. (2019). Chest X-ray as a diagnostic tool for pneumonia. Journal of Clinical Imaging Science, 9(3), 12-17. World Health Organization (WHO). (2020). Coronavirus disease (COVID-19) advice for the public. https://www.who.int Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swatter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level...
Read more
GALLERY