Artificial Neural Network-Based Approach for Lung Disease Detection Using Chest X-Ray Images
Computational Design: Journal of Modern Informatics · 30.09.2026 · 1 (2) · 94-101
DOI: 10.35730/mzf5ct79 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational Design: Journal of Modern Informatics, online erschienen am 30.09.2026. Verfasst von Aditya Adit und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Tuberculosis (TB) is an infectious disease caused by Mycobacterium tuberculosis that primarily affects the lungs and remains a significant global health concern, particularly in developing countries. Early and accurate detection of TB is essential to reduce transmission rates and improve patient outcomes. One of the most commonly used diagnostic methods is chest X-ray imaging, which allows visualization of lung abnormalities. However, the interpretation of X-ray images relies heavily on the expertise of radiologists and is often subject to human error, variability, and time constraints. This study aims to develop an automated system for tuberculosis detection using an Artificial Neural Network with a Convolutional Neural Network (CNN) approach. The proposed method involves several stages, including data collection, model design, training, and evaluation. The dataset used consists of chest X-ray images classified into two categories: normal and tuberculosis. Processing techniques such as image resizing, grayscale conversion, and normalization are applied to improve data quality and model performance. The CNN model is designed to automatically extract features from input images through convolutional layers, followed by pooling and fully connected layers for classification. The model is trained using the Adam optimizer and evaluated using performance metrics such as accuracy, precision, recall, and F1-score. Experimental results show that the proposed model achieves a high accuracy of up to 99.29%, with balanced precision and recall values, indicating its effectiveness in detecting tuberculosis cases. The results demonstrate that CNN-based models have strong potential in medical image classification and can be utilized as decision-support tools to assist healthcare professionals in diagnosing tuberculosis more efficiently and accurately. However, further research is needed to validate the model using larger and more diverse datasets and to improve its generalization capability for real-world clinical applications.
Zitieren
APA
Adit, A., & Shania, S. N. (2026). Artificial Neural Network-Based Approach for Lung Disease Detection Using Chest X-Ray Images. Computational Design: Journal of Modern Informatics, 1(2), 94-101. https://doi.org/10.35730/mzf5ct79
Vancouver
Adit A, Shania SN. Artificial Neural Network-Based Approach for Lung Disease Detection Using Chest X-Ray Images. Computational Design: Journal of Modern Informatics. 2026;1(2):94-101. doi:10.35730/mzf5ct79
BibTeX
@article{Adit2026,
author = {Adit, Aditya and Shania, Shania Nabila},
title = {Artificial Neural Network-Based Approach for Lung Disease Detection Using Chest X-Ray Images},
journal = {Computational Design: Journal of Modern Informatics},
year = {2026},
volume = {1},
number = {2},
pages = {94--101},
doi = {10.35730/mzf5ct79}
}
EUVIMED