A Comprehensive Approach to Brain Tumor Classification and Stage Classification Using Neural Networks and K-Means Segmentation

Abstract

The proposed optimized brain tumor detection method employs a dual-module framework combining advanced image processing, feature extraction, and classification to improve diagnostic accuracy. Brain MRI images are first enhanced using adaptive Wiener filtering for effective noise reduction. Discriminative features are extracted using a Radial Basis Function (RBF) neural network and classified through a Support Vector Machine (SVM) to identify tumor types, including meningioma, glioma, and pituitary tumors. Detected tumors are further analyzed for stage determination—early, intermediate, or advanced—using Convolutional Neural Networks (CNN) and K-means clustering-based segmentation. This integrated approach enables accurate tumor identification and staging, supporting improved treatment planning, timely clinical intervention, and enhanced patient outcomes in medical imaging applications.

Introduction

Brain tumors present a significant global health challenge due to high mortality, complex pathology, and treatment disparities linked to a country’s development level. Early and accurate detection is critical for improving survival, and MRI plays a central role by providing high-resolution, non-invasive imaging of tumor anatomy, composition, and boundaries.

Recent advances in machine learning and deep learning have enhanced MRI-based tumor analysis. Techniques like CNNs, hybrid learning frameworks, and K-means clustering improve automated tumor segmentation, feature extraction, and classification, overcoming limitations of manual or semi-automatic approaches. However, many studies focus on either segmentation or classification, with limited integrated solutions addressing tumor type and stage simultaneously.

The proposed method uses a dual-module framework:

1. Pre-processing: MRI images undergo resizing, Gaussian and adaptive Wiener filtering, and contrast enhancement to improve quality and highlight tumor regions.
2. Feature extraction and classification: Discriminative features are extracted using Radial Basis Function neural networks and classified via Support Vector Machines (SVM) to detect tumor types (glioma, meningioma, pituitary).
3. Tumor segmentation and staging: For tumor-positive cases, K-means clustering segments the tumor, and CNNs classify its stage (early, intermediate, advanced).

This integrated approach enables precise tumor detection and staging, providing actionable insights for treatment planning and timely clinical intervention.

Conclusion

In conclusion, the proposed dual-module system presents an effective approach for optimized brain tumor detection and staging by integrating advanced image processing and machine learning techniques. Adaptive Wiener filtering enhances image quality, while Radial Basis Function (RBF) neural networks enable reliable feature extraction. Support Vector Machine (SVM) classification accurately distinguishes tumor types, including meningioma, glioma, and pituitary tumors. Furthermore, the combination of Convolutional Neural Networks (CNN) with K-means–based segmentation enables precise tumor staging into early, intermediate, and advanced levels. This integrated framework improves diagnostic accuracy, supports timely clinical intervention, and facilitates informed treatment planning, demonstrating strong potential for practical clinical application and future research in brain tumor diagnosis.

References

[1] Z. Khazaei, E. Goodarzi, V. Borhaninejad, F. Iranmanesh, H. Mirshekar pour, B. Mirzaei, H. Naemi, S. M. Bechashk, I. Darvishi, R. E. Sarabi, and A. Naghibzadeh-Tahami, ‘‘The association between incidence and mortality of brain cancer and human development index (HDI): An ecological study,’’ BMC Public Health, vol. 20, p. 1696, Nov. 2020. [2] T. S. Armstrong, M. Z. Cohen, J. Weinberg, and M. R. Gilbert, ‘‘Imaging techniques in neuro-oncology,’’ Seminars Oncol. Nursing, vol. 20, pp. 231–239, Nov. 2004. [3] H. W. Kim, L. Van Assche, R. B. Jennings, W. B. Wince, C. J. Jensen, W. G. Rehwald, D. C. Wendell, L. Bhatti, D. M. Spatz, M. A. Parker, and E. R. Jenista, ‘‘Relationship of T2 weighted MRI myocardial hyperintensity and the ischemic area-at-risk,’’ Circulation Res., vol. 117, no. 3, pp. 254–265, 2015. [4] W.Deng,Q.Shi,K.Luo,Y.Yang,andN.Ning,‘‘Braintumorseg mentation based on improved convolutional neural network in combination with non quantifiable local texture feature,’’ J. Med. Syst., vol. 43, no. 6, p. 152, 2019. [5] A. Lundervold and A. Lundervold, ‘‘An overview of deep learning in medical imaging focusing on MRI,’’ Zeitschrift für Medizinische Physik, vol. 29, no. 2, pp. 102–127, 2019. [6] Y. Jiang, J. Hou, X. Xiao, and H. Deng, ‘‘A brain tumor segmentation new method based on statistical thresholding and multiscale CNN,’’ in Proc. Int. Conf. Intell. Comput., 2018, pp. 235–245. [7] M.Hssayeni, ‘‘Computed tomography images for intracranial hemorrhage detection and segmentation,’’ Intracranial Hemorrhage Segmentation Using Deep Convolutional Model. Data, vol. 5, no. 1, p. 14, Mar. 2020. [8] T. A. Soomro and J. Gao, ‘‘Neural network based denoised methods for retinal fundus images and MRI brain images,’’ in Proc. Int. Joint Conf. Neural Netw. (IJCNN), Vancouver, BC, Canada, Jul. 2016, pp. 1151–1157. [9] E.F. Badran, E. G. Mahmoud, and N.Hamdy,‘‘Analgorithm for detecting brain tumors in MRI images,’’ in Proc. Int. Conf. Comput. Eng. Syst., Nov. 2010, pp. 368–373. [10] T. A. Soomro, L. Zheng, A. J. Afifi, A. Ali, S. Soomro, M. Yin, and J. Gao, ‘‘Image segmentation for MR brain tumor detection using machine learning: A review,’’ IEEE Rev. Biomed. Eng., vol. 16, pp. 70–90, 2023. [11] A. Selvapandian and K. Manivannan, ‘‘Fusion based glioma brain tumor detection and segmentation using ANFIS classification,’’ Comput. Methods Programs Biomed., vol. 166, pp. 33–38, Nov. 2018. [12] M. Sharif, J. Amin, M. Raza, M. Yasmin, and S. C. Satapathy, ‘‘An integrated design of particle swarm optimization (PSO) with fusion of features for detection of brain tumor,’’ Pattern Recognit. Lett., vol. 129, pp. 150–157, Jan. 2020. [13] A. Kumar, M. Ramachandran, A. H. Gandomi, R. Patan, S. Lukasik, and R. K. Soundarapandian, ‘‘A deep neural network based classifier for brain tumor diagnosis,’’ Appl. Soft Comput., vol. 82, Sep. 2019, Art. no. 105528. [14] F. Özyurt, E. Sert, E. Avci, and E. Dogantekin, ‘‘Brain tumor detection based on convolutional neural network with neutrosophic expert maximum fuzzy sure entropy,’’ Measurement, vol. 147, Dec. 2019, Art. no. 106830. [15] A.R.Raju, P. Suresh, and R. R. Rao, ‘‘Bayesian HCS based multi-SVNN: Aclassification approach for brain tumor segmentation and classification using Bayesian fuzzy clustering,’’ Biocybern. Biomed. Eng., vol. 38, no. 3, pp. 646–660, 2018. [16] B. Yin, C. Wang, and F. Abza, ‘‘New brain tumor classification method based on an improved version of whale optimization algorithm,’’ Biomed. Signal Process. Control, vol. 56, Feb. 2020, Art. no. 101728. [17] A. Krol and B. Gimi, ‘‘Medical imaging 2017: Biomedical applica tions in molecular, structural, and functional imaging,’’ in Society of Photo-Optical Instrumentation Engineers. Bellingham, WA, USA: SPIE, 2017. [18] M. Mittal, L. M. Goyal, S. Kaur, I. Kaur, A. Verma, and D. J. Hemanth, ‘‘Deep learning based enhanced tumor segmentation approach for MR brain images,’’ Appl. Soft Comput., vol. 78, pp. 346–354, May 2019. [19] M. A. Mohammed, M. K. Abd Ghani, R. I. Hamed, D. A. Ibrahim, and M. K. Abdullah, ‘‘Artificial neural networks for automatic segmentation and identification of nasopharyngeal carcinoma,’’ J. Comput. Sci., vol. 21, pp. 263–274, Jul. 2017. [20] A. Rehman, S. Naz, M. I. Razzak, F. Akram, and M. Imran, ‘‘A deep learning-based framework for automatic brain tumors classification using transfer learning,’’ Circuits, Syst., Signal Process., vol. 39, pp. 757–775, Sep. 2020.

Copyright

Copyright © 2026 G Chandraiah , G. Prakash Babu, K Praveena, J.V. Sai Sujan , K. Guru Mahesh , P. Girish Venkat Sai, K Ramyasri . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.