Abstract
Magnetic Resonance Imaging (MRI) is a technique used to assess various regions of the body and is useful in medical diagnosis. Because of this, it is important to maintain the clarity of the MRI images that are often degraded by different noises, particularly Gaussian and Rician. In this paper a comprehensive evaluation of different denoising methods for brain MRI images, including classical, hybrid, and deep learning methods is conducted. The methods evaluated include BM3D (Block-Matching and 3D Filtering), PCA (Principal Component Analysis)-based denoising, PCA combined with median filtering, a proposed hybrid approach (combining PCA, median filtering, and bilateral filtering with Rician bias correction), and DnCNN (Denoising Convolutional Neural Network) trained on custom MRI image patches. The metrics used to assess these denoising methods include PSNR (Peak Signal to Noise Ratio), SSIM (Structural Similarity Index), and histogram-based metrics like Bhattacharya distance, intersection, and correlation. In summary, the DnCNN method shows the best results across all noise types and levels, demonstrating high structural preservation. However, the proposed hybrid method also demonstrates competitive results compared to DnCNN and better results in comparison to classical methods like BM3D and PCA-based denoising methods. From this comparison, it can be concluded that while the deep learning-based method is overall the best for denoising, the hybrid method can also be seen as an alternative in cases of limited training resources.
References
Andria, Gregorio, Filippo Attivissimo, and Anna Maria Lucia Lanzolla. "A statistical approach for MR and CT images comparison." Measurement 46, no. 1 (2013): 57-65.
Dr. Y. MaryReeja,” Comparative Analysis of Noise Reduction Techniques for Brain MRI Image”, J. Electrical Systems 20-10s (2024): 6068-6077
Gudbjartsson, Hákon, and Samuel Patz. "The Rician distribution of noisy MRI data." Magnetic resonance in medicine 34, no. 6 (1995): 910-914.
Sriani, S., Ilka Zufria, and Mhd Syahnan. "Improved Digital Image Quality Using the Gaussian Filter Method." IJISTECH (International Journal of Information System and Technology) 5, no. 5 (2022): 556-563.
George, Ginu, Rinoy Mathew Oommen, Shani Shelly, Stephie Sara Philipose, and Ann Mary Varghese. "A survey on various median filtering techniques for removal of impulse noise from digital image." In 2018 conference on emerging devices and smart systems (ICEDSS), IEEE, (2018): 235-238.
Kaur, Bobbinpreet, Ayush Dogra, and Bhawna Goyal. "Comparative analysis of bilateral filter and its variants for magnetic resonance imaging." The Open Neuroimaging Journal 13, no. 1 (2020).
Komoto, Yuki, Jiho Ryu, and Masateru Taniguchi. "Total variation denoising-based method of identifying the states of single molecules in break junction data." Discover Nano 19, no. 1 (2024): 20.
Alkinani, Monagi H., and Mahmoud R. El-Sakka. "Patch-based models and algorithms for image denoising: a comparative review between patch-based images denoising methods for additive noise reduction." EURASIP journal on image and video processing 2017, no. 1 (2017): 58.
Li, YingJiang, Jiangwei Zhang, and Maoning Wang. "Improved BM3D denoising method." IET Image Processing 11, no. 12 (2017): 1197-1204.
Phan, Tran Dang Khoa. "A spatially variant high-order variational model for Rician noise removal." PeerJ Computer Science 9 (2023): e1579.
Wang, Wenjing. "An improved denoising model for convolutional neural network." In Journal of Physics: Conference Series, vol. 1982, no. 1, p. 012169. IOP Publishing, 2021.
Mudrova, M., and Aleš Procházka. "Principal component analysis in image processing." In Proceedings of the MATLAB technical computing conference, Prague, (2005): 1-4.
Li, Shiao, Fei Wang, and Song Gao. "New non-local mean methods for MRI denoising based on global self-similarity between values." Computers in Biology and Medicine 174 (2024): 108450.
Henriques, Rafael Neto, Andrada Ianuş, Lisa Novello, Jorge Jovicich, Sune N. Jespersen, and Noam Shemesh. "Efficient PCA denoising of spatially correlated redundant MRI data." Imaging Neuroscience 1 (2023): 1-26.
Han, Trong-Thanh, Hinh Nguyen Van, and Phat Nguyen Huu. "Denoising Method for MRI Images Using Modified BM3D Filter with Complex Network and Artificial Neural Networks." Journal of Electrical and Computer Engineering 2024, no. 1 (2024): 2606485.
Wang, Yuan-Bin, and Hai-Long Huang. "Image denoising based on adaptive sector rotation median filter." In Journal of Physics: Conference Series, vol. 1769, no. 1, p. 012056. IOP Publishing, 2021.
Zhang, Qi, Jingyu Xiao, Chunwei Tian, Jerry Chun‐Wei Lin, and Shichao Zhang. "A robust deformed convolutional neural network (CNN) for image denoising." CAAI Transactions on Intelligence Technology 8, no. 2 (2023): 331-342.
Sara, Umme, Morium Akter, and Mohammad Shorif Uddin. "Image quality assessment through FSIM, SSIM, MSE and PSNR—a comparative study." Journal of Computer and Communications 7, no. 3 (2019): 8-18.
Bottenus, Nick, Brett C. Byram, and Dongwoon Hyun. "Histogram matching for visual ultrasound image comparison." IEEE transactions on ultrasonics, ferroelectrics, and frequency control 68, no. 5 (2020): 1487-1495.
Forero, Manuel G., Carlos Arias-Rubio, and Brigete Tatiana González. "Analytical comparison of histogram distance measures." In Iberoamerican Congress on Pattern Recognition, Cham: Springer International Publishing, (2018): 81-90.
Liang, Jian, Pengxu Chen, and Mian Wu. "Research on an image denoising algorithm based on deep network learning." In Journal of Physics: Conference Series, vol. 1802, no. 3, p. 032112. IOP Publishing, 2021.
Zhao, Shutian, Fan Xiao, James F. Griffith, Ruokun Li, and Weitian Chen. "Denoising of volumetric magnetic resonance imaging using multi-channel three-dimensional convolutional neural network with applications on fast spin echo acquisitions." Quantitative Imaging in Medicine and Surgery 14, no. 9 (2024): 6517.
Meyer, Maria Ines, Ezequiel de la Rosa, Nuno Barros, Roberto Paolella, Koen Van Leemput, and Diana M. Sima. "An augmentation strategy to mimic multi-scanner variability in MRI." In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), IEEE, (2021): 1196-1200.
Shou, Qinyang, Chenyang Zhao, Xingfeng Shao, Kay Jann, Hosung Kim, Karl G. Helmer, Hanzhang Lu, and Danny JJ Wang. "Transformer‐based deep learning denoising of single and multi‐delay 3D arterial spin labeling." Magnetic resonance in medicine 91, no. 2 (2024): 803-818.
Kanal, Kalpana M., Jonathan H. Chung, Jin Wang, Puneet Bhargava, Jennifer R. Kohr, William P. Shuman, and Brent K. Stewart. "Image noise and liver lesion detection with MDCT: a phantom study." American Journal of Roentgenology 197, no. 2 (2011): 437-441.
Olesen, O. F., et al. (2022). Evaluation of MRI denoising techniques using BrainWeb simulated datasets. BrainWeb. https://doi.org/10.3389/frai.2021.642731.
Yang, Haibo, Shengjie Zhang, Xiaoyang Han, Botao Zhao, Yan Ren, Yaru Sheng, and Xiao-Yong Zhang. "Denoising of 3D MR images using a voxel-wise hybrid residual MLP-CNN model to improve small lesion diagnostic confidence." In International Conference on Medical Image Computing and Computer-Assisted Intervention, Cham: Springer Nature Switzerland, (2022): 292-302.