Download pdf
Research on an Intelligent Pneumonia Diagnosis Model Based on Improved Convolutional Neural Networks Using Chest X-ray Images
- 1 Shandong University, Weihai, China
* Author to whom correspondence should be addressed.
Abstract
Pneumonia, a common health concern today, requires early and accurate diagnosis. Chest X-ray examinations play a critical role in the early detection of pneumonia. To enhance diagnostic accuracy, this study utilizes a deep learning-based convolutional neural network (CNN) model, trained on a dataset of 5,216 chest X-ray images obtained from pediatric patients aged 1-5 years at Guangzhou Women and Children's Medical Center. Among these, 3,875 images show signs of pneumonia and 1,341 images are normal, serving as the training and testing data for the model. By incorporating Dropout techniques and Batch Normalization methods, the model’s robustness and generalization ability were significantly improved. Experimental results demonstrate that the model achieves a diagnostic accuracy of 97.83%, which will effectively alleviate physicians’ workload and holds substantial clinical application value.
Keywords
Medical Image Classification, Convolutional Neural Network, Chest X-ray Pneumonia Diagnosis
[1]. Geng, J., Chang, Y., Zhang, B., Wang, S., & Zhang, F. (2023). Diagnostic performance of a deep learning model based on coronary CT angiography for coronary heart disease. Chinese Journal of Medical Imaging Technology, 31(7), 706–712.
[2]. Hui, R., Gao, X., & Tian, Z. (2017). A preliminary screening method for Alzheimer’s disease using CT brain image classification based on deep learning. China Medical Equipment, 32(12), 5.
[3]. Zhou, Q., Wang, J., Tang, W., & Zhang, R. (2020). Application of convolutional neural network in automatic detection and classification of adult rib fractures on CT images. Imaging Diagnosis and Interventional Radiology, 29(1), 5.
[4]. Gu, J., Shi, H., Yang, L., Shen, Y., Wang, Z., Feng, Q., et al. (2021). Clinical significance of a deep learning algorithm based on enhanced CT in differentiating gastrointestinal stromal tumors of the stomach with diameter ≤5 cm. Chinese Journal of Gastrointestinal Surgery, 24(9), 8.
[5]. Zhang, J., Chen, F., Xue, X., Zhang, S., Yao, L., Wang, X., et al. (2018). Value of MRI radiomics based on support vector machine in differentiating pathological types of primary liver cancer. Chinese Journal of Radiology, 52(5), 5.
[6]. Fu, T., Yao, Z., Ding, H., Xu, Z., Yang, M., & Yu, J., et al. (2019). Value analysis of computer-aided diagnosis in monitoring liver fibrosis progression in chronic hepatitis B patients. National Medical Journal of China, 99(7), 491–495.
[7]. Miao, L., Peng, M., Wang, T., Chen, G., Yin, X., & Wu, G. (2022). Prediction of hemorrhagic transformation after acute ischemic stroke based on MRI radiomics and machine learning. Magnetic Resonance Imaging, 13(3), 5.
[8]. Huang, X., & Ma, J. (2024). Research on liver tumor detection algorithms based on deep convolutional neural networks. Journal of Ningxia Normal University, 45(7), 84–91.
[9]. Liu, J., Wu, J., Liu, A., Bai, Y., Zhang, H., & Yan, M. (2022). Preoperative diagnosis of hepatocellular carcinoma with biliary tumor thrombus based on deep learning methods. Journal of University of Science and Technology of China, 52(12), 47–57.
[10]. Yin, X., Li, D., Tu, Y., & Shan, B. (2020). Recognition of subthreshold depression patients based on deep learning and multimodal medical image fusion. Chinese Journal of Medical Imaging Technology, 36(8), 5.
Cite this article
Li,X. (2025). Research on an Intelligent Pneumonia Diagnosis Model Based on Improved Convolutional Neural Networks Using Chest X-ray Images. Theoretical and Natural Science,113,9-17.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of ICBioMed 2025 Symposium: AI for Healthcare: Advanced Medical Data Analytics and Smart Rehabilitation
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).