Scholarlink

<p>The rapid spread of the novel coronavirus disease 2019 (COVID-19) pandemic underscores the need for early and accurate detection to enable effective treatment and containment. In this context, computational methods have shown considerable promise. This study presents an efficient end-to-end deep learning approach for detecting COVID-19, among other human coronavirus (HCoV) diseases. The proposed approach employs genomic image processing (GIP) techniques to convert complete and partial HCoV genome sequences into grayscale genomic images using the frequency chaos game representation method. These images are analyzed using a novel deep learning model, DeepCOVID-19, in conjunction with the pre-trained AlexNet model. Evaluation on a comprehensive dataset of diverse HCoV variants demonstrates that the DeepCOVID-19 model achieves an accuracy of 99.84%, outperforming existing state-of-the-art methods. The proposed GIP-based framework provides a robust and scalable solution for the rapid and reliable detection of COVID-19.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Detection of COVID-19 using genomic image processing techniques with end-to-end structure deep learning models

  • 期刊论文

  • 发表日期：

    2025年12月12日

查看全文
  • Muhammed S. Hammad,
  • Vidan F. Ghoneim,
  • Walid I. Al-atabany,
  • Mai S. Mabrouk

摘要

The rapid spread of the novel coronavirus disease 2019 (COVID-19) pandemic underscores the need for early and accurate detection to enable effective treatment and containment. In this context, computational methods have shown considerable promise. This study presents an efficient end-to-end deep learning approach for detecting COVID-19, among other human coronavirus (HCoV) diseases. The proposed approach employs genomic image processing (GIP) techniques to convert complete and partial HCoV genome sequences into grayscale genomic images using the frequency chaos game representation method. These images are analyzed using a novel deep learning model, DeepCOVID-19, in conjunction with the pre-trained AlexNet model. Evaluation on a comprehensive dataset of diverse HCoV variants demonstrates that the DeepCOVID-19 model achieves an accuracy of 99.84%, outperforming existing state-of-the-art methods. The proposed GIP-based framework provides a robust and scalable solution for the rapid and reliable detection of COVID-19.