Advancing the Quality of Chest X-Ray Images to Support Better Classification Outcomes Utilizing Convolutional Neural Networks

Maiyanga K.A.; O.J.Oluwale; Oluguwasen M.O.

doi:https://doi.org/10.47001/CJESR/2025.201003

Authors

Maiyanga K.A.

Department of Electronic Engineering, University of Nigeria, Nigeria

O.J.Oluwale

Department of Electrical Engineering, Nnamdi Azikiwe University, Awka, Anambra State, Nigeria

Oluguwasen M.O.

Department of Electrical Engineering, Nnamdi Azikiwe University, Awka, Anambra State, Nigeria

Abstract

The role of medical imaging is pivotal in the diagnosis of numerous diseases, particularly respiratory conditions. However, noise artifacts, including salt-and-pepper noise and Gaussian noise, can significantly impair the quality of chest X-ray (CXR) images, potentially resulting in misdiagnoses. This research aims to improve CXR images by employing noise removal techniques followed by histogram equalization to enhance overall image quality. Two datasets are utilized: one from a publicly available source and another collected from laboratory environments. The latter dataset is subjected to a manual noise removal process to ensure superior image clarity. Subsequently, a Convolutional Neural Network (CNN) model, specifically ResNet-50, is applied for classification across both datasets. A comparative analysis is conducted to demonstrate that images that have been manually denoised achieve greater accuracy than those that remain noisy. The results of the experiments substantiate the effectiveness of the proposed approach in enhancing image quality and improving diagnostic accuracy.

Keywords

Chest X-Ray Image processing CXR Salt and Pepper Noise Gaussian Noise Respiratory system Convolutional Neural Network CNN

Citation of this Article

Maiyanga K.A., O.J.Oluwale, & Oluguwasen M.O. (2025). Advancing the Quality of Chest X-Ray Images to Support Better Classification Outcomes Utilizing Convolutional Neural Networks. Current Journal of Engineering and Science Research. 2(1), 15-18. Article DOI: https://doi.org/10.47001/CJESR/2025.201003

References

K. Suzuki, "A review of deep learning in medical imaging: Image segmentation and disease detection," Artificial Intelligence in Medicine, 2020.
Sharif, Muhammad, Ayyaz Hussain, Muhammad Arfan Jaffar, and Tae-Sun Choi. "Fuzzy similarity based non local means filter for Rician noise removal." Multimedia tools and applications 74, no. 15 (2015): 5533-5556.
Zhang, Xinyuan, GuirongHou, Jianhua Ma, Wei Yang, Bingquan Lin, Yikai Xu, Wufan Chen, and Yanqiu Feng. "Denoising MR images using non-local means filter with combined patch and pixel similarity." PloS one 9, no. 6 (2014): e100240.
Zhou, Min-Xiong, Xu Yan, Hai-Bin Xie, Hui Zheng, Dongrong Xu, and Guang Yang. "Evaluation of nonlocal means based denoising filters for diffusion kurtosis imaging using a new phantom." PloS one 10, no. 2 (2015): e0116986.
Yang, Jian, Jingfan Fan, Danni Ai, Shoujun Zhou, Songyuan Tang, and Yongtian Wang. "Brain MR image denoising for Rician noise using pre-smooth non-local means filter." Biomedical engineering online 14, no. 1 (2015): 2.
Manjón, José V., Pierrick Coupé, and Antonio Buades. "MRI noise estimation and denoising using non-local PCA." Medical image analysis 22, no. 1 (2015): 35-47.
M. Anwar, M. Majid, A. Qayyum, M. Awais, M. Alnowami, and S. M. Khan, "Medical image analysis using convolutional neural networks: A review," Journal of Medical Systems, 2018.
H. J. Kang, J. H. Lee, and Y. H. Cho, "Noise reduction methods for medical X-ray images using deep learning techniques," IEEE Transactions on Medical Imaging, 2021.
R. Wang and Y. Zhao, "Denoising of medical images using wavelet transform and CNN-based models," IEEE Access, 2020.
P. G. Howard, B. S. Deveraj, and M. I. Patel, "Enhancement of chest X-ray images using adaptive histogram equalization," IEEE Transactions on Biomedical Engineering, 2019.
T. Y. Liu, H. C. Hsu, and K. M. Lin, "A novel deep learning framework for lung disease classification using enhanced chest X-ray images," IEEE Journal of Biomedical and Health Informatics, 2021.
M. R. Alshaye, A. H. Raza, and C. J. Simmons, "Noise reduction in X-ray images using hybrid filtering techniques," IEEE Transactions on Image Processing, 2021.
N. Gupta and P. Singh, "Comparative analysis of histogram equalization techniques in medical imaging applications," IEEE Signal Processing Letters, 2021.

[1] K. Suzuki, "A review of deep learning in medical imaging: Image segmentation and disease detection," Artificial Intelligence in Medicine, 2020.

[2] Sharif, Muhammad, Ayyaz Hussain, Muhammad Arfan Jaffar, and Tae-Sun Choi. "Fuzzy similarity based non local means filter for Rician noise removal." Multimedia tools and applications 74, no. 15 (2015): 5533-5556.

[3] Zhang, Xinyuan, GuirongHou, Jianhua Ma, Wei Yang, Bingquan Lin, Yikai Xu, Wufan Chen, and Yanqiu Feng. "Denoising MR images using non-local means filter with combined patch and pixel similarity." PloS one 9, no. 6 (2014): e100240.

[4] Zhou, Min-Xiong, Xu Yan, Hai-Bin Xie, Hui Zheng, Dongrong Xu, and Guang Yang. "Evaluation of nonlocal means based denoising filters for diffusion kurtosis imaging using a new phantom." PloS one 10, no. 2 (2015): e0116986.

[5] Yang, Jian, Jingfan Fan, Danni Ai, Shoujun Zhou, Songyuan Tang, and Yongtian Wang. "Brain MR image denoising for Rician noise using pre-smooth non-local means filter." Biomedical engineering online 14, no. 1 (2015): 2.

[6] Manjón, José V., Pierrick Coupé, and Antonio Buades. "MRI noise estimation and denoising using non-local PCA." Medical image analysis 22, no. 1 (2015): 35-47.

[7] M. Anwar, M. Majid, A. Qayyum, M. Awais, M. Alnowami, and S. M. Khan, "Medical image analysis using convolutional neural networks: A review," Journal of Medical Systems, 2018.

[8] H. J. Kang, J. H. Lee, and Y. H. Cho, "Noise reduction methods for medical X-ray images using deep learning techniques," IEEE Transactions on Medical Imaging, 2021.

[9] R. Wang and Y. Zhao, "Denoising of medical images using wavelet transform and CNN-based models," IEEE Access, 2020.

[10] P. G. Howard, B. S. Deveraj, and M. I. Patel, "Enhancement of chest X-ray images using adaptive histogram equalization," IEEE Transactions on Biomedical Engineering, 2019.

[11] T. Y. Liu, H. C. Hsu, and K. M. Lin, "A novel deep learning framework for lung disease classification using enhanced chest X-ray images," IEEE Journal of Biomedical and Health Informatics, 2021.

[12] M. R. Alshaye, A. H. Raza, and C. J. Simmons, "Noise reduction in X-ray images using hybrid filtering techniques," IEEE Transactions on Image Processing, 2021.

[13] N. Gupta and P. Singh, "Comparative analysis of histogram equalization techniques in medical imaging applications," IEEE Signal Processing Letters, 2021.