Noise reduction in X-ray imaging has been a critical area of research due to its direct impact on image clarity and diagnostic accuracy. This noise primarily results from the reduction of X-ray power, which is necessary to minimize radiation exposure and associated health risks. Traditional noise reduction methods, such as wavelet domain thresholding techniques like BayesShrink, have been widely explored. However, their effectiveness is often limited due to the Poisson-distributed nature of X-ray noise, making standard thresholding approaches suboptimal. In this study, we propose an advanced denoising framework that integrates wavelet domain processing with a genetic algorithm to optimize the BayesShrink threshold. To further enhance image quality, we employ a multi-layer perceptron (MLP) neural network, which improves clarity by refining local pixel intensities. Despite its effectiveness, neural network-based denoising alone struggles to eliminate high-intensity noise. To address this limitation, we introduce a directional adaptive median filter to suppress severe noise while preserving crucial image structures. Since median filtering may compromise edge details, we incorporate an edge reconstruction step to restore essential structural information. Simulation results demonstrate that our proposed approach outperforms conventional methods in terms of Peak Signal-to-Noise Ratio (PSNR), Mean Structural Similarity Index (MSR), and Contrast-to-Noise Ratio (CNR). The findings indicate that our hybrid method provides significantly improved image clarity compared to existing denoising techniques, making it a promising solution for enhancing X-ray image quality while maintaining diagnostic integrity.
[1] Okamoto, T., Furui, S., Ichiji, H., Yoshino, S., Lu, J., & Yahagi, T. (2004). Noise reduction in digital radiography using wavelet packet based on noise characteristics. Journal of Signal Processing, 8(6), 485-494. https://doi.org/10.2299/jsp.8.485
[2] Nowak, R. D., & Baraniuk, R. G. (1999). Wavelet-domain filtering for photon imaging systems. IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing Society, 8(5), 666-678. https://doi.org/10.1109/83.760334
[3] Ozkan, M. K., Erdem, A. T., Sezan, M. I., & Tekalp, A. M. (1992). Efficient multiframe Wiener restoration of blurred and noisy image sequences. IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing Society, 1(4), 453-476. https://doi.org/10.1109/83.199916
[4] Wang, Z., & Zhang, D. (1999). Progressive switching median filter for the removal of impulse noise from highly corrupted images. IEEE Transactions on Circuits and Systems II Analog and Digital Signal Processing, 46(1), 78-80. https://doi.org/10.1109/82.749102
[5] Donoho, D. L., Johnstone, I. M., Kerkyacharian, G., & Picard, D. (1995). Wavelet shrinkage: Asymptopia? Journal of the Royal Statistical Society, 57(2), 301-337. https://doi.org/10.1111/j.2517-6161.1995.tb02032.x
[6] Atkinson, I., Kamalabadi, F., Mohan, S., & Jones, D. L. (2004). Wavelet-based 2-D multichannel signal estimation. In Proceedings 2003 International Conference on Image Processing (Cat. No. 03CH37429) (pp. 33-38). IEEE. https://doi.org/10.1109/icip.2003.1246636
[7] Chang, S. G., Yu, B., & Vetterli, M. (2000). Adaptive wavelet thresholding for image denoising and compression. IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing Society, 9(9), 1532-1546. https://doi.org/10.1109/83.862633
[8] Wang, L., Lu, J., Li, Y., Yahagi, T., & Okamoto, T. (2005). Noise reduction using wavelet with application to medical X-ray image. In 2005 IEEE International Conference on Industrial Technology (pp. 33-38). IEEE. https://doi.org/10.1109/ICIT.2005.1600606
[9] Kavchak, M. A., & Budman, H. M. (1998). Adaptive neural network architectures for nonlinear function estimation. In Proceedings of the 1998 American Control Conference. ACC (IEEE Cat. No. 98CH36207). Philadelphia, PA, USA. https://doi.org/10.1109/ACC.1998.694629
Yin, Z., Shi, W., Wu, Z., & Zhang, J. (2022). Multilevel wavelet-based hierarchical networks for image compressed sensing. Pattern Recognition, 129, 108758. https://doi.org/10.1016/j.patcog.2022.108758
Chen, X.-L., Tian, M., & Yao, W.-B. (2005). GPR signals de-noising by using wavelet networks. In 2005 International Conference on Machine Learning and Cybernetics (pp. 869-873). IEEE. https://doi.org/10.1109/icmlc.2005.1527766
Zhang, X.-P. (2002). Space-scale adaptive noise reduction in images based on thresholding neural network. In 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing (Vol. 4, pp. 2185-2188). IEEE. https://doi.org/10.1109/ICASSP.2001.941313
Li, Y., Lu, J., Wang, L., & Takashi, Y. (2009). Denoising by using multineural networks for medical X-ray imaging applications. Neurocomputing, 72(13-15), 2884-2891. https://doi.org/10.1016/j.neucom.2008.07.019
Mastriani, M., & Giraldez, A. E. (2018). Microarrays denoising via smoothing of coefficients in wavelet domain. arXiv. http://arxiv.org/abs/1807.11571
Liu, P., & Li, H. (2002). Image restoration techniques based on fuzzy neural networks. Science in China Series F: Information Sciences, 45(4), 273-285. https://doi.org/10.1360/02yf9024
Norouzzadeh, Y., & Katebi, S. D. (2006). Application of ANFIS in Wavelet Denoising. In 6th Iranian Conference on Fuzzy Systems and 1st Islamic World Conference on Fuzzy Systems (Islamic Azad University of Shiraz).
Norouzzadeh, Y., & Rashidi, M. (2011). Image denoising in wavelet domain using a new thresholding function. In International Conference on Information Science and Technology (pp. 62-66). Nanjing, China. https://doi.org/10.1109/ICIST.2011.5765347
Norouzzadeh, Y., & Katebi, S. D. (2007). Threshold estimation in wavelet domain using fuzzy rules. In 4th Iranian Conference on Machine Vision and Image Processing.
Antoniadis, A., Bigot, J., & Sapatinas, T. (2001). Wavelet estimators in nonparametric regression: A comparative simulation study. Journal of Statistical Software, 6(6). https://doi.org/10.18637/jss.v006.i06
Donoho, D. L. (1995). De-noising by soft-thresholding. IEEE Transactions on Information Theory, 41(3), 613-627. https://doi.org/10.1109/18.382009
Donoho, D. L., & Johnstone, I. M. (1994). Ideal spatial adaptation by wavelet shrinkage. Biometrika, 81(3), 425-455. https://doi.org/10.1093/biomet/81.3.425
Donoho, D. L., & Johnstone, I. M. (1995). Adapting to unknown smoothness via wavelet shrinkage. Journal of the American Statistical Association, 90(432), 1200-1224. https://doi.org/10.1080/01621459.1995.10476626
Soltanian-Zadeh, H., Windham, J. P., & Yagle, A. E. (1995). A multidimensional nonlinear edge-preserving filter for magnetic resonance image restoration. IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing Society, 4(2), 147-161. https://doi.org/10.1109/83.342189
Cincotti, G., Loi, G., & Pappalardo, M. (2001). Frequency decomposition and compounding of ultrasound medical images with wavelet packets. IEEE Transactions on Medical Imaging, 20(8), 764-771. https://doi.org/10.1109/42.938244
Zamani,M. , Azadi,S. and Rahmani Seryasat,O. (2021). Noise Reduction in Medical X-Ray Images Using Wavelet and Neural Networks. Transactions on Machine Intelligence, 4(1), 36-52. doi: 10.47176/TMI.2021.36
MLA
Zamani,M. , , Azadi,S. , and Rahmani Seryasat,O. . "Noise Reduction in Medical X-Ray Images Using Wavelet and Neural Networks", Transactions on Machine Intelligence, 4, 1, 2021, 36-52. doi: 10.47176/TMI.2021.36
HARVARD
Zamani M., Azadi S., Rahmani Seryasat O. (2021). 'Noise Reduction in Medical X-Ray Images Using Wavelet and Neural Networks', Transactions on Machine Intelligence, 4(1), pp. 36-52. doi: 10.47176/TMI.2021.36
CHICAGO
M. Zamani, S. Azadi and O. Rahmani Seryasat, "Noise Reduction in Medical X-Ray Images Using Wavelet and Neural Networks," Transactions on Machine Intelligence, 4 1 (2021): 36-52, doi: 10.47176/TMI.2021.36
VANCOUVER
Zamani M., Azadi S., Rahmani Seryasat O. Noise Reduction in Medical X-Ray Images Using Wavelet and Neural Networks. Trans. Mach. Intell., 2021; 4(1): 36-52. doi: 10.47176/TMI.2021.36
