Classification of Medical Images Through Convolutional Neural Network Modification Method

Syed Kashif Badshah1Noor Badshah
Additional contact information
Syed Kashif Badshah1Noor Badshah: Department of Basic Science sand Islamiat, University of Engineering and Technology,Peshawar,Pakistan

International Journal of Innovations in Science & Technology, 2024, vol. 6, issue 5, 216-226

Abstract: 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.

Keywords: Image Classification; Fuzzy Membership; VGG-19 Modified Model (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journal.50sea.com/index.php/IJIST/article/view/775/1378 (application/pdf)
https://journal.50sea.com/index.php/IJIST/article/view/775 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:abq:ijist1:v:6:y:2024:i:5:p:216-226

Access Statistics for this article

International Journal of Innovations in Science & Technology is currently edited by Prof. Dr. Syed Amer Mahmood

More articles in International Journal of Innovations in Science & Technology from 50sea
Bibliographic data for series maintained by Iqra Nazeer ().