Medical Radiology and Radiation Safety. 2026. Vol. 71. № 2

DOI:10.33266/1024-6177-2026-71-2-107-114

Muaayed F. Al-Rawi ¹, Muhanned AL-Rawi ²

Image Segmentation of Brain Tumors Using K-means Cluster Technique

¹ College of Engineering, Mustansiriyah University, Baghdad, Iraq

² University College of Wisdom, Iraq

Contact person: Muaayed F. Al-Rawi, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

Brain tumor segmentation aims to differentiate between various tumor tissues, including active cells, necrotic core, and edema, and normal brain tissues composed of cerebrospinal fluid (CSF), white matter (WM), and gray matter (GM). Over the last several years, studies that use magnetic resonance imaging (MRI) to segment brain tumors have garnered an increasing amount of interest. This is mostly due to the fact that MRI scans are non-invasive and provide an excellent contrast between soft tissue and bone. Computer-aided techniques for segmenting brain tumors are maturing and nearing integration into routine clinical applications. Researchers have developed these groundbreaking approaches over approximately twenty years. The objective of this article is to provide a K-means clustering technique for the purpose of brain tumor segmentation using magnetic resonance imaging (MRI). The K-means clustering technique is an unsupervised approach that is used for the purpose of separating the region of interest from the background. However, in order to increase the overall quality of the image, a partial stretching improvement is first done to the image before the K-means technique is implemented.

Keywords: MRI, image segmentation, cluster algorithm, brain tumor

For citation: Muaayed F. Al-Rawi, Muhanned AL-Rawi. Image Segmentation of Brain Tumors Using K-means Cluster Technique. Medical Radiology and Radiation Safety. 2026;71(2):107–114. DOI:10.33266/1024-6177-2026-71-2-107-114

References

1. Muaayed F. Al-Rawi, Izz K. Abboud, Nasir A. Al-Awad. Using Machine Learning Algorithms to Detect Cancer Automatically. Medical Radiology and Radiation Safety. 2025;70;3:83-89.
2. URL: https://www.who.int/.
3. Izz K. Abboud, Muaayed F. Al-Aawi, Nasir A. Al-Awad. Digital Medical Image Encryption Approach in Real-Time Applications. System Research & Information Technologies. 2024;1:26-32.
4. Muaayed F. Al-Rawi, Izz K. Abboud, Nasir A. Al-Awad. Novel Approach Using Transfer Deep Learning for Brain Tumor Prediction. Medical Radiology and Radiation Safety. 2021;69;3:81-85.
5. Lotlikar V.S., Satpute N., Gupta A. Brain Tumor Detection Using Machine Learning and Deep Learning: A Review. Current Medical Imaging. 2022;18;6:1-19.
6. Kovesi B., Boucher J.M., Saoudi S. Stochastic K-means Algorithm for Vector Quantization. Pattern Recognition Letters. 2001;22:603-610.
7. Gdalyahu Y., Weinshall D., Wermen M. Self-Organization in Vision: Stochastic Clustering for Image Segmentation, Perceptual Grouping, and Image Database Organization. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016;23;12:1053-1074.
8. Veenman C.J., Reinders M.J.T., Backer E. A Maximum Variance Cluster Algorithm”, IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018;24;9:1273-1280.
9. Carson C., Greenspan H. Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018;24;8:1026-1038.
10. Atsushi K., Masayuki N., Means K. Algorithm Using Texture Directionality for Natural Image Segmentation. IEICE Technical Report. Image Engineering. 2019;97;8:17-22.

 PDF (RUS) Full-text article (in Russian)

Conflict of interest. The authors declare no conflict of interest.

Financing. The study had no sponsorship.

Contribution. Article was prepared with equal participation of the authors.

Article received: 20.01.2026. Accepted for publication: 25.02.2026.