Elevating X-ray Image Classification Performance with wavelet Fusion and deep Learning

Authors

  • Ali Khalil Raad Dean of the faculty of sciences and arts at the Islamic University of Lebanon
  • Dalia Adil Almuhsin Department of Computer Science, College of education for Pure Science, University of Basrah

Keywords:

Selected:X-ray Image classification, CNN, wavelet transform, Image fusion, deep learning

Abstract

Medical imaging has seen a significant advancement in recent years, with the introduction of multi-spectral X-ray imaging being one notable development. However, traditional image fusion methods such as weighted averaging or maximum intensity projection may not be sufficient to address the complexities of X-ray images. In response, a new deep learning-based multi-spectral X-ray image fusion method has been developed. This method utilizes Convolutional Neural Networks(CNNs) utilizes deep learning algorithms to combine multiple images obtained from different X-ray energy levels into a single image with higher resolution and improve quality. The problem statement highlights the limitations of traditional X-ray imaging methods and the challenges in developing an effective image fusion method. The proposed approach’s contribution is a step towards improving the quality and accuracy of medical imaging, leading to better patient outcomes and more efficient healthcare practices. The provided results indicate that the proposed model achieved an accuracy of 95% on the training data and 90% on the test data, with room for improvement. The limitation of the dataset and the algorithm used for classification are discussed as potential reasons for not achieving higher accuracy. Further research is required to develop specialized deep learning models for X-ray image fusion and explore other algorithms and techniques to address the challenges related to the dataset and the algorithm used for classification.

Downloads

Download data is not yet available.

References

G. Akçay et al., “Performance evaluation of a spectral CT system for lung nodule detection,” Medical Physics, vol. 47, no. 2, pp. 680–694, 2020, DOI:10.1002/mp.13876

Z. Sun et al., “Ship classification in high-resolution SAR images based on CNN regional feature fusion,” in Proc. 2021 CIE Int. Conf. Radar (Radar), 2021, pp. 1445–1449, DOI: 10.1109/Radar52297.2021.000267.

M. Krenkel et al., “Advanced x-ray imaging for non-destructive testing,” Materials Evaluation, vol. 77, no. 3, pp. 346–352, 2019, DOI: 10.32548/me.77.3.346.

L. Yongtao, L. Yan, and P. Yuxing, “A new multi-focus image fusion method based on improved PCNN and multi-scale transformation,” Signal Processing: Image Communication, vol. 85, p. 115913, 2020, DOI: 10.1016/j.image.2020.115913.

A. Toet, M. A. Hogervorst, and A. W. M. Smeulders, “Image fusion: From historically early approaches to current domain-specific applications,” Journal of Electronic Imaging, vol. 27, no. 4, p. 041203, 2018, DOI: 10.1117/1.JEI.27.4.041203.

Y. Zhang, Q. Cheng, and J. Huang, “Deep learning for image fusion: a comprehensive review,” Information Fusion, vol. 69, pp. 15–42, 2021, DOI: 10.1016/j.inffus.2020.12.004.

G. Bhatnagar and Q. M. J. Wu, “Deep learning-based image fusion: A survey of the state-of-the-art,” Information Fusion, vol. 57, pp. 104–118, 2020, doi: 10.1016/j.inffus.2020.01.003.

Y. Wang, Y. Cai, and S. Zhang, “A review of image fusion methods based on deep learning,” Information Fusion, vol. 45, pp. 153–178, 2019, DOI: 10.1016/j.inffus.2018.08.003.

Y. Zhou et al., “VGG-FusionNet: A feature fusion framework from CT scan and chest X-ray images based deep learning for COVID-19 detection,” in Proc. 2022 IEEE Int. Conf. Data Mining Workshops (ICDMW), 2022, pp. 1–9, DOI: 10.1109/ICDMW58026.2022.00054.

S. Lafraxo and M. el Ansari, “CoviNet: Automated COVID-19 detection from X-rays using deep learning techniques,” in Proc. 2020 6th IEEE Congr. Inf. Sci. Technol. (CiSt), 2020, pp. 489–494, DOI: 10.1109/CiSt49399.2021.9357250.

B. M. Anakha, G. Shaji, and S. Geetha, “Detecting COVID-19 from chest X-ray images using deep learning,” in Proc. 2021 5th Int. Conf. Inf. Syst. Comput. Networks (ISCON), 2021, pp. 1–4, DOI: 10.1109/ISCON52037.2021.9702491.

Z. Karhan and F. Akal, “Covid-19 classification using deep learning in chest X-ray images,” in Proc. 2020 Medical Technologies Congress (TIPTEKNO), 2020, pp. 1–4, DOI: 10.1109/TIPTEKNO50054.2020.9299315.

S. Nefoussi, A. Amamra, and I. A. Amarouche, “A comparative study of deep learning networks for COVID-19 recognition in chest X-ray images,” in Proc. 2020 2nd Int. Workshop Human-Centric Smart Environ. Health Well-being (IHSH), 2021, pp. 237–241, DOI: 10.1109/IHSH51661.2021.9378703.

Z. Sun et al., “Ship classification in high-resolution SAR images based on CNN regional feature fusion,” in Proc. 2021 CIE Int. Conf. Radar (Radar), 2021, pp. 1445–1449, DOI: 10.1109/Radar52297.2021.000267.

X. Wang et al., “ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases,” in Proc. 2017 IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 3462–3471, DOI: 10.1109/CVPR.2017.369.

V. H. Phung and E. J. Rhee, “A high-accuracy model average ensemble of convolutional neural networks for classification of cloud image patches on small datasets,” Appl. Sci., vol. 9, no. 21, p. 4500, 2019, DOI: 10.3390/app9214500.

Downloads

Published

30-06-2025

Issue

Section

Articles

How to Cite

Elevating X-ray Image Classification Performance with wavelet Fusion and deep Learning. (2025). Basrah Researches Sciences, 51(1), 15. https://jou.jobrs.edu.iq/index.php/home/article/view/183