EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Classification of Medical Images Through Convolutional Neural Network Modification Method

Syed Kashif Badshah, Noor Badshah

International Journal of Innovations in Science and Technology · 27.05.2024 · 216

DOI: 10.33411/ijist/775 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovations in Science and Technology, online erschienen am 27.05.2024. Verfasst von Syed Kashif Badshah und 1 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The COVID-19 positive, tuberculosis and pneumonia, share the trait of being able to be identified using radiological investigations, such as Chest X-ray (CXR) images. This paper aims to distinguish between four classes, including tuberculosis (TB), COVID-19 positive, healthy, and pneumonia using CXR images. Many deep-learning models such as a Convolutional Neural Network (CNN) have been developed for the Classification of CXR images. Deep learning-based models such as CNN offer significant advantages over traditional methods in the classification of diseases like TB, COVID-19, pneumonia, and healthy states. They provide higher accuracy, automation, early detection, reduced subjectivity, and resource efficiency, ultimately leading to improved patient care and outcomes. However, well-liked CNNs are massive models that require a lot of data to achieve optimal accuracy. In this paper, we propose a new CNN model that can be used to distinguish between different classes of CXR images. This model proves to be effective in classifying different diseases such as pneumonia, COVID-19, and tuberculosis. This study has used 6326 CXR images dataset containing COVID-19 positive, tuberculosis, and pneumonia and has normal images. In this dataset, 80% of the CXR images are taken for the training purpose and 20% are taken for the validation purpose, of the proposed CNN model. The proposed CNN modified model with parameter adjustment as well as using categorical cross-entropy as a loss function obtains the highest classification accuracy of 98.51% with a precision, recall, and F1 score of 0.98, 0.985, and 0.98 respectively.

Zitieren

APA

Badshah, S. K., & Badshah, N. (2024). Classification of Medical Images Through Convolutional Neural Network Modification Method. International Journal of Innovations in Science and Technology, 216. https://doi.org/10.33411/ijist/775

Vancouver

Badshah SK, Badshah N. Classification of Medical Images Through Convolutional Neural Network Modification Method. International Journal of Innovations in Science and Technology. 2024:216. doi:10.33411/ijist/775

BibTeX
@article{Badshah2024,
  author = {Badshah, Syed Kashif and Badshah, Noor},
  title = {Classification of Medical Images Through Convolutional Neural Network Modification Method},
  journal = {International Journal of Innovations in Science and Technology},
  year = {2024},
  pages = {216},
  doi = {10.33411/ijist/775}
}
Kostenlos starten →