2020/03/26 by Asmaa Abbas, Abbas, Asmaa, Mohammed M. Abdelsamea +3 · 2 citations
Computer Science · Medicine · #AI in cancer detection #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Radiomics and Machine Learning in Medical Imaging #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2003.13815
openalex publication_date 2020/03/26 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Chest X-ray is the first imaging technique that plays an important role in\nthe diagnosis of COVID-19 disease. Due to the high availability of large-scale\nannotated image datasets, great success has been achieved using convolutional\nneural networks (CNNs) for image recognition and classification. However, due\nto the limited availability of annotated medical images, the classification of\nmedical images remains the biggest challenge in medical diagnosis. Thanks to\ntransfer learning, an effective mechanism that can provide a promising solution\nby transferring knowledge from generic object recognition tasks to\ndomain-specific tasks. In this paper, we validate and adapt our previously\ndeveloped CNN, called Decompose, Transfer, and Compose (DeTraC), for the\nclassification of COVID-19 chest X-ray images. DeTraC can deal with any\nirregularities in the image dataset by investigating its class boundaries using\na class decomposition mechanism. The experimental results showed the capability\nof DeTraC in the detection of COVID-19 cases from a comprehensive image dataset\ncollected from several hospitals around the world. High accuracy of 95.12%\n(with a sensitivity of 97.91%, a specificity of 91.87%, and a precision of\n93.36%) was achieved by DeTraC in the detection of COVID-19 X-ray images from\nnormal, and severe acute respiratory syndrome cases.\n