| Autor: |
Kadry, Seifedine, Abualigah, Laith, González Crespo, Rubén, Verdú, Elena, Damasevicius, Robertas, Singh, Vijendra, Rajinikanth, Venkatesan |
| Předmět: |
|
| Zdroj: |
Procedia Computer Science; 2024, Vol. 235, p3438-3446, 9p |
| Abstrakt: |
Computerized disease detection systems (CDDs) have proven effective for automatic screening in recent years. Among the standard procedures in hospitals for faster and more accurate diagnosis is medical imaging-based disease screening. We aim to develop a CDD that detects COVID-19 using chest X-rays pre-trained vision transformers (PVTs). This scheme includes the following steps: (1) collecting images and resizing them, (2) implementing PVT for feature extraction, and (3) binary classifying the results and validating the proposed schemes. To prove the merit of the developed scheme, 4800 images (2400 normal and 2400 COVID-19) are analyzed. MLP classifiers verify the PVT performance using patch sizes of 6, 12, and 24. A patch size 24 results in 97.5% accuracy for the proposed CDD system. When patch sizes are increased to 12, accuracy increases to over 98%. For this specific task, smaller patch sizes are more effective. These high-accuracy results demonstrate the effectiveness of the developed scheme for detecting COVID-19 in chest X-rays. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Supplemental Index |
| Externí odkaz: |
|
