AI-Powered Detection of COVID-19 and Lung Diseases from Chest X-Rays: Boosting Accuracy with CNNs and Top-K Algorithms

The COVID-19 epidemic has highlighted the need for easier and more precise diagnoses.  Traditional techniques, such as PCR tests, are helpful but can be time-consuming and laborious.  In order to further enhance picture quality, this study presents a novel method for identifying COVID-19 and other lung disorders utilizing chest X-rays, convolutional neural networks (CNNs), and histogram equalization.  The 1 823 X-ray pictures in the collection were divided into three categories: regular, COVID-19-positive, and additional lung infections.  Based on the combination of CNN and Topk algorithms, our proposed approach reached 98.45% accuracy.  These promising results suggest that our method may expedite the identification of COVID-19, reducing its consequences on the healthcare system.  The dataset will be expanded in the future, along with sophisticated techniques and the use of our created Top-k algorithms to improve decision-making.

COVID-19
pulmonary diseases
згорткова нейронна мережа
матриця помилок
Topk algorithms
diagnosis
  1. Mathieu E., Ritchie H., Rodés-Guirao L., et al. Coronavirus (COVID-19) Cases.  Our World in Data (2020).  https://ourworldindata.org/covid-cases.
  2. Gupta V., Jain N., Sachdeva J., et al.  Improved COVID-19 detection with chest x-ray images using deep learning.  Multimedia Tools and Applications.  81 (26), 37657–37680 (2022).
  3. Careful.Online.  The Future of Healthcare: 2024 AI Impact Analysis.  Careful Online Publications (2024).  https://careful.online/future-healthcare-ai-2024/.
  4. Aya T., Handri K. E., Fouzia O.  Automated Detection of Malicious Software in Medical Environments Using Deep Learning.  International Conference on the Global Summit of Digital Health.  100–106 (2025).
  5. Gupta V., Jain N., Sachdeva J., et al.  Improved COVID-19 detection with chest x-ray images using deep learning.  Multimedia Tools and Applications.  81 (1), 37657–37680 (2020).
  6. Rahman T., Khandakar A., Qiblawey Y., et al.  Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images.  Computers in Biology and Medicine.  132, 104319 (2021).
  7. Ozturk T., Talo M., Yildirim E. A., et al.  Automated detection of COVID-19 cases using deep neural networks with X-ray images.  Computers in Biology and Medicine.  121, 103792 (2020).
  8. Beddiar D. R., Oussalah M., Muhammad U., Seppänen T.  A Deep learning based data augmentation method to improve COVID-19 detection from medical imaging.  Knowledge-Based Systems.  280, 110985 (2023).
  9. El Handri K., El Ahrach S., Touil M.  A new synesthesia-based approach for AI in healthcare.  International Journal of Research and Ethics.  5 (1), (2022).
  10. El Handri K., Idrissi A.  Parallelization of $Top_k$ Algorithm Through a New Hybrid Recommendation System for Big Data in Spark Cloud Computing Framework.  IEEE Systems Journal.  15 (4), 4876–4886 (2020).
  11. El Handri K., Idrissi A.  Correlations and Hierarchical Clustering Investigation Between Weather and SARS-CoV-2.  Recent Advances in Computer Science and Communications (Formerly: Recent Patents on Computer Science).  15 (6), 859–867 (2022).
  12. Handri K. E., Idrissi A.  Comparative study of Topk based on Fagin's algorithm using correlation metrics in cloud computing {QoS}.  International Journal of Internet Technology and Secured Transactions.  10 (1/2), 143 (2020).
  13. Tang S., Wang C., Nie J., Kumar N., Zhang Y., Xiong Z.  EDL-COVID: Ensemble Deep Learning for COVID-19 Case Detection From Chest X-Ray Images.  IEEE Transactions on Industrial Informatics.  17 (9), 6539–6549 (2021).
  14. Abdullah M., Abrha F. B., Kedir B., Tamirat Tagesse T.  A Hybrid Deep Learning CNN model for COVID-19 detection from chest X-rays.  Heliyon.  10 (5), e26938 (2024).
  15. Luo X., Chen X., Yao Y., Yao Y.  MVMSGAT: Integrating Multiview, Multi-Scale Graph Convolutional Networks with Biological Prior Knowledge for Predicting Bladder Cancer Response to Neoadjuvant Therapy.  Applied Sciences.  14 (2), 669 (2024).
  16. Tahir A. M., Chowdhury M. E. H., Khandakar A., et al.  COVID-19 infection localization and severity grading from chest X-ray images.  Computers in Biology and Medicine.  139, 105002 (2021).
  17. Tahir A. M., Chowdhury M. E. H., Qiblawey Y., et al.  COVID-QU-Ex Dataset.  Kaggle (2021).
  18. An J., Zhang N., Mahmoud W., Denis M.  A COVID-19 CXR Image Recognition Method Based on Deep Transfer Learning.  2024 International Joint Conference on Neural Networks (IJCNN).  1–6 (2024).
  19. Goodfellow I., Bengio Y., Courville A.  Deep Learning. MIT Press  (2016).
  20. François-Lavet V., Henderson P., Islam R., Bellemare M. G., Pineau J., et~al.  An introduction to deep reinforcement learning.  Foundations and Trends in Machine Learning.  11 (3–4), 219–354 (2018).
  21. Handri K. E., Benedress L. G., Wakrim L., Lamzabi S., Idrissi A.  AI-Based QoS Optimization in Post-Disaster Ad Hoc Networks: Top-K Path Enumeration with Multicriteria Decision Analysis.  2024 IEEE 4th International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA).  561–566 (2024).
  22. Lamzabi S., Madi B. A. W., Benyoussef M., et al.  Minimizing the Viruses Propagation in Interconnected Complex Networks.  2024 IEEE 4th International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA).  544–549 (2024).
  23. Wang W., Xu Y., Gao R., Lu R., Han K., Wu G., Tan W.  Detection of SARS-CoV-2 in different types of clinical specimens.  JAMA.  323 (18), 1843–1844 (2020).
  24. Chen J., Wu L., Zhang J., Zhang L., Gong D., Zhao Y., Chen Q., Huang S., Yang M., Yang X., et al.  Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography.  Scientific Reports.  10 (1), 19196 (2020).
  25. Zhang L., Luo M., Liu J., Chang X., Yang Y., Hauptmann A. G.  Deep Top-$k$ Ranking for Image–Sentence Matching.  IEEE Transactions on Multimedia.  22 (3), 775–785 (2019).
  26. Zheng Y., Zheng Y., Suehiro D., Uchida S.  Top-rank convolutional neural network and its application to medical image-based diagnosis.  Pattern Recognition.  120, 108138 (2021).
  27. Petersen F., Kuehne H., Borgelt C., Deussen O.  Differentiable Top-k Classification Learning.  Proceedings of the 39th International Conference on Machine Learning.  162, 17656–17668 (2022).