MRI brain image denoising and tumor detection using 1-D and 2-D empirical mode decomposition
Giang Hong Nguyen1, 2, Yen Thi Hoang Hua1, Linh Chi Nguyen1 and Liet Van Dang1
Faculty of Physics and Engineering Physics,University of Science, Viet Nam National University,Ho Chi Minh City,Vietnam1
Faculty of Physics and Engineering Physics,Cao Thang Technical College,Ho Chi Minh City,Vietnam2
Faculty of Physics and Engineering Physics,Cao Thang Technical College,Ho Chi Minh City,Vietnam2
Corresponding Author : Giang Hong Nguyen
Recieved : 08-February-2025; Revised : 18-January-2026; Accepted : 21-January-2026
Abstract
Magnetic resonance imaging (MRI) is a non-invasive imaging modality widely used for the early diagnosis of brain tumors, as it provides clear visualization of brain structures and enables effective discrimination between normal and abnormal tissues. However, MRI scans are often contaminated with Rician noise during the image acquisition process, which degrades image quality and may lead to diagnostic inaccuracies. This article aims to apply one-dimensional (1-D) and two-dimensional (2-D) empirical mode decomposition (EMD) as the first stage of a computer-aided diagnosis (CADx) system for noise reduction and tumor detection. A hybrid approach combining 2-D EMD and non-local means (NLM) filtering is employed to suppress noise. The proposed method is evaluated for Rician noise reduction using simulated images from the BrainWeb dataset and for denoising real MRI images from the Figshare dataset. Performance is compared with five commonly used filtering techniques based on denoised images, residual images, and five image quality metrics. The experimental results demonstrate that the proposed approach produces superior denoised images compared to the benchmark methods and performs better than direct filtering of noisy images. For brain tumor identification, a 1-D EMD-based thresholding technique is applied to nine MRI images from the Figshare dataset representing three different types of brain tumors. Compared with ground truth annotations, the proposed method outperforms three widely used tumor detection techniques, achieving 99% accuracy and specificity, 97–100% sensitivity, and 68–89% precision.
Keywords
Magnetic resonance imaging, Rician noise, Empirical mode decomposition, Non-local means filtering, Brain tumor detection, Computer-aided diagnosis.
Cite this article
Nguyen GH, Hua YTH, Nguyen LC, Dang LV. MRI brain image denoising and tumor detection using 1-D and 2-D empirical mode decomposition. International Journal of Advanced Technology and Engineering Exploration. 2026;13(134):102-122. DOI : 10.19101/IJATEE.2025.121220203
References
[1]
Jareena BD, Chokkalingam SP. MRI-based brain tumour detection and classification using random forest algorithm. In international conference on intelligent systems and sustainable computing 2024 (pp. 77-91). Singapore: Springer Nature Singapore.
[2]
Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians. 2021; 71(3):209-49.
[3]
https://www.nfcr.org/cancer-types/cancer-types-brain-cancer/ Accessed 22 July 2025.
[4]
Asif RN, Naseem MT, Ahmad M, Mazhar T, Khan MA, Khan MA, et al. Brain tumor detection empowered with ensemble deep learning approaches from MRI scan images. Scientific Reports. 2025; 15(1):1-22.
[5]
Zhang L, Wen X, Li JW, Jiang X, Yang XF, Li M. Diagnostic error and bias in the department of radiology: a pictorial essay. Insights Into Imaging. 2023; 14(1):1-12.
[6]
Sharma BP, Purwar RK. Computer-aided detection and diagnosis of breast cancer: a review. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal. 2024; 13:1-21.
[7]
Hu Y, Xu H, Zhu X, Wake HN. V-DDPM: MRI rician noise removal model based on VST and DDPM. In international conference on acoustics, speech and signal processing (ICASSP) 2024 (pp. 2250-4). IEEE.
[8]
Xu Y, Quan R, Xu W, Huang Y, Chen X, Liu F. Advances in medical image segmentation: a comprehensive review of traditional, deep learning and hybrid approaches. Bioengineering. 2024; 11(10):1-42.
[9]
Akshath Raj V, Nayak SG, Thalengala A. A hybrid framework for muscle artifact removal in EEG: combining variational mode decomposition, stationary wavelet transform, and canonical correlation analysis. Cogent Engineering. 2025; 12(1): 2514941.
[10]
Radwane GAM. Efficient image fusion method using improved bi-dimensional empirical mode decomposition. International Journal of Image and Data Fusion. 2024; 15(1):44-72.
[11]
Bhushan M, Agwekar A. De-noising MRI image of high-density different noise using linear and nonlinear threshold filter. International Journal of Innovative Research in Technology and Management. 2024; 8(4):24-35.
[12]
Ashraf R, Nisha R, Shamim F, Shams S. Cutting through the noise: a three-way comparison of median, adaptive median, and non-local means filter for MRI images. Sir Syed University Research Journal of Engineering & Technology. 2024; 14(1):1-6.
[13]
Sharma M, Dogra A, Goyal B, Gupta A, Saikia MJ. Detail-preserving denoising of CT and MRI images via adaptive clustering and non-local means algorithm. Scientific Reports. 2025; 15(1):1-22.
[14]
Awudong B, Yakupu P, Yan J, Li Q. Research and implementation of denoising algorithm for brain MRIs via morphological component analysis and adaptive threshold estimation. Mathematics. 2024; 12(5):1-21.
[15]
Li S, Wang F, Gao S. New non-local mean methods for MRI denoising based on global self-similarity between values. Computers in Biology and Medicine. 2024; 174:1-10.
[16]
Liu C, Zhang L. A novel denoising algorithm based on wavelet and non-local moment mean filtering. Electronics. 2023; 12(6):1-13.
[17]
Ng YJ, Sim KS. A review of brain early infarct image contrast enhancement using various histogram equalization techniques. International Journal on Advanced Science, Engineering & Information Technology. 2024; 14(6):1849-60.
[18]
El SH. Denoising and contrast enhancement of CT brain image using median filter and HE. African Journal of Advanced Pure and Applied Sciences (AJAPAS). 2024; 3(1):141-8.
[19]
Kushwaha S, Amuthachenthiru K, Narasimharao J, Kumar D, Gadde SS. Development of advanced noise filtering techniques for medical image enhancement. In 5th international conference on intelligent communication technologies and virtual mobile networks (ICICV) 2024 (pp. 906-12). IEEE.
[20]
Zangana HM, Mustafa FM. Hybrid image denoising using wavelet transform and deep learning. EAI Endorsed Transactions on AI and Robotics. 2024; 3(1):1-9.
[21]
Gurrola-ramos J, Alarcon T, Dalmau O, Manjón JV. MRI rician noise reduction using recurrent convolutional neural networks. IEEE Access. 2024; 12:128272-84.
[22]
Yang BC, Xu FZ, Zhao Y, Yao TY, Hu HY, Jia MY, et al. Complete ensemble empirical mode decomposition and wavelet algorithm denoising method for bridge monitoring signals. Buildings. 2024; 14(7):1-14.
[23]
Hong NG, Thi HHY, Van DL. MRI brain tumor segmentation using bidimensional empirical mode decomposition and morphological operations. In the international conference on intelligent systems & networks 2023 (pp. 1-11). Singapore: Springer Nature Singapore.
[24]
Yang L, Zhang M, Cheng J, Zhang T, Lu F. Retina images classification based on 2D empirical mode decomposition and multifractal analysis. Heliyon. 2024; 10(6):1-18.
[25]
Rubio D, Sassano N, Morvidone M, Piotrkowski R. Application of bidimensional empirical mode decomposition for particle identification and size determination. International Journal of Applied Mathematics, Computational Science and Systems Engineering. 2024; 6:186-92.
[26]
Swaroopa HN, Jagadale BN, Gupta A. Brain MRI image analysis and segmentation using machine learning. International Journal of Scientific Research in Science, Engineering and Technology. 2023; 10(6):202-12.
[27]
Malathi M, Sekar K, Mahendrakan K, Sinthia P. A hybrid clustering approach for medical image segmentation. In computational imaging and analytics in biomedical engineering 2024 (pp. 187-200). Apple Academic Press.
[28]
Javeed MD, Nagaraju R, Chandrasekaran R, Rajulu G, Tumuluru P, Ramesh M, et al. Brain tumor segmentation and classification with hybrid clustering, probabilistic neural networks. Journal of Intelligent & Fuzzy Systems. 2023; 45(4):6485-500.
[29]
Cè M, Chiriac MD, Cozzi A, Macrì L, Rabaiotti FL, Irmici G, et al. Decoding radiomics: a step-by-step guide to machine learning workflow in hand-crafted and deep learning radiomics studies. Diagnostics. 2024; 14(22):1-33.
[30]
Liu Z, Ma C, She W, Xie M. Innovative multi-class segmentation for brain tumor MRI using noise diffusion probability models and enhancing tumor boundary recognition. Scientific Reports. 2024; 14(1):1-9.
[31]
Gupta A, Dixit M, Mishra VK, Singh A, Dayal A. Brain tumor segmentation from MRI images using deep learning techniques. In international advanced computing conference 2022 (pp. 434-48). Cham: Springer Nature Switzerland.
[32]
Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences. 1998; 454(1971):903-95.
[33]
Nunes JC, Bouaoune Y, Delechelle E, Niang O, Bunel P. Image analysis by bidimensional empirical mode decomposition. Image and vision computing. 2003; 21(12):1019-26.
[34]
Buades A, Coll B, Morel JM. A non-local algorithm for image denoising. In computer society conference on computer vision and pattern recognition 2005 (pp. 60-5). IEEE.
[35]
Buades A, Coll B, Morel JM. Non-local means denoising. Image Processing on Line. 2011; 1:208-12.
[36]
Liu D, Chen X. Image denoising based on improved bidimensional empirical mode decomposition thresholding technology. Multimedia Tools and Applications. 2019; 78(6):7381-417.
[37]
Krinidis S, Krinidis M, Chatzis V. An empirical method for threshold selection. International Journal of Signal Processing, Image Processing and Pattern Recognition. 2012; 5(2):101-14.
[38]
Le VT, Van DL. Enhancement of mammographic images based on wavelet denoise and morphological contrast enhancement. International Journal of Image, Graphics and Signal Processing. 2023; 6:28-40.
[39]
Bao P, Zhang L. Noise reduction for magnetic resonance images via adaptive multiscale products thresholding. IEEE Transactions on Medical Imaging. 2003; 22(9):1089-99.
[40]
Nadeem MW, Goh HG, Ponnusamy V, Andonovic I, Khan MA, Hussain M. A fusion-based machine learning approach for the prediction of the onset of diabetes. Healthcare. 2021; 9(10):1-16.
[41]
https://brainweb.bic.mni.mcgill.ca/ Accessed 22 July 2025.
[42]
https://figshare.com/articles/dataset/brain_tumor_dataset/1512427 Accessed 22 July 2025.
[43]
https://www.mathworks.com/matlabcentral/fileexchange/54748-fast-nonlocal-means. Accessed 22 July 2025.
[44]
https://www.mathworks.com/matlabcentral/fileexchange/71270-fast-and-adaptive-multivariate-and-multidimensional-emd. Accessed 22 July 2025.
[45]
Chaudhari A, Kulkarni J. Noise estimation in single coil MR images. Biomedical Engineering Advances. 2021; 2:1-9.
[46]
Manjón JV, Carbonell-caballero J, Lull JJ, García-martí G, Martí-bonmatí L, Robles M. MRI denoising using non-local means. Medical Image Analysis. 2008; 12(4):514-23.
[47]
https://www.mathworks.com/matlabcentral/fileexchange/14995-anisotropic-diffusion-perona-malik. Accessed 22 July 2025.
[48]
https://github.com/gpeyre/matlab-toolboxes/blob/master/toolbox_sparsity/perform_tv_denoising.m. Accessed 22 July 2025.
[49]
Chen K, Lin X, Hu X, Wang J, Zhong H, Jiang L. An enhanced adaptive non-local means algorithm for rician noise reduction in magnetic resonance brain images. BMC Medical Imaging. 2020; 20(1):1-9.