Keywords
Image Enhancement
Preprocessing
Adaptive Histogram Equalization
How to Cite
Abstract
The treatment of biomedical images through preprocessing and enhancement techniques draws the attention of everyone in the field of medical imaging due to the fact that such treatments will contribute to the improvement of the diagnostic accuracy. The present study investigates preprocessing and enhancement techniques applied to MRI brain tumor imaging. The tumor regions, consequently, become more visible and clearer. The methods used are Gaussian filtering, adaptive histogram equalization, and wavelet-based enhancement that remove the noise and make the image brighter at the same time. The power of the combination of these methods in yielding great images was astounding; the image quality measures used registered very significant changes—Peak Signal-to-Noise Ratio (PSNR) increased from 28,6 dB to 36,8 dB, Structural Similarity Index (SSIM) from 0,82 to 0,94, and Mean Squared Error (MSE) decreased by approximately 40 %. The tumor boundary delineation got better as a result of such advancements leading to more accurate segmentation and classification. This research verified that good preprocessing and enhancement were prerequisites for the reliable analysis of brain MRI images, besides, it pointed out the future directions of diagnostic and machine learning applications in the area of biomedical image processing.
References
1. Acharya UR, et al. Automated detection of brain abnormality using MRI images: A review. IEEE Rev Biomed Eng. 2019.
2. Zhang Y, et al. A survey on deep learning applications in MRI-based brain tumor analysis. Front Oncol. 2020.
3. Somasundaram K, Kalaiselvi T. Automatic brain extraction methods and image preprocessing techniques for brain MRI: A survey. J Med Syst. 2017;41(12):204.
4. Gonzalez RC, Woods RE. Digital image processing. 4th ed. London: Pearson; 2018.
5. Pizer SM, et al. Adaptive histogram equalization and its variations. Comput Vis Graph Image Process. 1987;39(3):355–68.
6. Acharya UR, et al. Hybrid filtering techniques for enhanced brain MRI visualization. Biomed Signal Process Control. 2018; 47:1–13.
7. Vinoth S, Rajasekar C, Sathish P, Sureshkumar V, Yasminebegum A, Ahammad SH, et al. Optimization of process parameters on wire cut electrical discharge machining and surface integrity studies of AA6070/MgO composites. J Phys Conf Ser. 2023;2484(1):012012.
8. Ahammad SH, Jayaraj R, Shibu S, Sujatha V, Prathima C, Leo LM, et al. Advanced model-based machine learning technique for early-stage prediction of ankylosing spondylitis under timely analysis with featured textures. Multimed Tools Appl. 2024;83(26):68393–413.
9. Kumar MS, Syed Inthiyaz, Krishna Vamsi C, Ahammad SH, Sai Lakshmi K, Venu Gopal P, et al. Power optimization using dual SRAM circuit. Int J Innov Technol Explor Eng. 2019;8(8):1032–6.
10. Srinivasa Reddy K, Suneela B, Inthiyaz S, Hasane Ahammad S, Kumar GNS, Mallikarjuna Reddy A. Texture filtration module under stabilization via random forest optimization methodology. Int J Adv Trends Comput Sci Eng. 2019;8(3):458–69.
11. Rehman A, et al. An efficient preprocessing approach for brain MRI classification using CNN. Comput Biol Med. 2022; 148:105780.
12. Tripathi R, Singh D. Improving MRI brain tumor images using multi-scale wavelet-based enhancement. Multimed Tools Appl. 2020; 79:21071–96.
13. Kumar A, Rathore Y. Noise reduction in MRI images using hybrid wavelet filtering. Biomed Signal Process Control. 2021; 68:102741.
14. Hossain M, et al. A comparative study of image enhancement techniques for brain MRI images. Procedia Comput Sci. 2019; 152:367–74.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2026 V Rajesh, B Rakesh Babu, Sk Hasane Ahammad, Ebrahim E. Elsayed (Author)