Brain Tumor Classifications Using MRI Scans with Deep Learning

, Anastasija

doi:10.25673/123092

Proceedings of International Conference on Applied Innovation in IT · 2025/12/22 · Vol. 13 · Issue 5 · pp. 637–642

Brain Tumor Classifications Using MRI Scans with Deep Learning

Anastasija Stefanovska and Hristijan Gjoreski

📄 Download PDF DOI: 10.25673/123092

Abstract

This paper focuses on the detection and classification of brain tumors using MRI images and Deep Learning methods. The dataset consists of 7,023 MRI scans representing healthy brains and brains with glioma, meningioma, or pituitary tumors. We developed and evaluated Convolutional Neural Network (CNN) models of varying depth, combined with preprocessing techniques such as image resizing, limited augmentation, and validation set allocation to prevent overfitting. The study demonstrates that CNN-based approaches can achieve high accuracy in tumor classification, with the best model reaching an overall accuracy of 98.5%. Results show that the greatest misclassification occurred between glioma and meningioma, reflecting their similar MRI appearance. Further analysis confirms that these tumor types share overlapping visual characteristics, making them more challenging to separate. Overall, the findings highlight that well-designed architectures and carefully controlled preprocessing can significantly enhance automated brain tumor detection, offering valuable support for radiologists and contributing to more efficient, consistent, and reliable diagnostic workflows.

Keywords

Brain Tumor Magnetic Resonance Imaging Deep Learning Convolutional Neural Networks Medical Image Analysis.

References

D. Arulmani and R. Manickam, “Brain Tumors,” J Stud Res, vol. 13, no. 2, May 2024, doi: 10.47611/jsrhs.v13i2.6694.
D. N. Louis et al., “The 2021 WHO Classification of Tumors of the Central Nervous System: a summary,” Neuro-Oncology, vol. 23, no. 8, pp. 1231–1251, June 2021, doi: 10.1093/neuonc/noab106.
P. A. Patil and P. Giridhar, “Epidemiology and Demography of Brain Tumors,” Evidence based practice in Neuro-oncology. Springer Singapore, pp. 3–7, 2021. doi: 10.1007/978-981-16-2659-3_1.
M. Pichaivel, G. Anbumani, P. Theivendren, and M. Gopal, “An Overview of Brain Tumor,” Brain Tumors. IntechOpen, Apr. 20, 2022. doi: 10.5772/intechopen.100806.
M. K. Abd-Ellah, A. I. Awad, A. A. M. Khalaf, and H. F. A. Hamed, “A review on brain tumor diagnosis from MRI images: Practical implications, key achievements, and lessons learned,” Magnetic Resonance Imaging, vol. 61, pp. 300–318, Sept. 2019, doi: 10.1016/j.mri.2019.05.028.
M. A. Khan et al., “Multimodal Brain Tumor Classification Using Deep Learning and Robust Feature Selection: A Machine Learning Application for Radiologists,” Diagnostics, vol. 10, no. 8, p. 565, Aug. 2020, doi: 10.3390/diagnostics10080565.
A. Kumar, J. Kim, D. Lyndon, M. Fulham, and D. Feng, “An Ensemble of Fine-Tuned Convolutional Neural Networks for Medical Image Classification,” IEEE J. Biomed. Health Inform., vol. 21, no. 1, pp. 31–40, Jan. 2017, doi: 10.1109/jbhi.2016.2635663.
K. Kamnitsas et al., “Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation,” Medical Image Analysis, vol. 36, pp. 61–78, Feb. 2017, doi: 10.1016/j.media.2016.10.004.
M. Havaei et al., “Brain tumor segmentation with Deep Neural Networks,” Medical Image Analysis, vol. 35, pp. 18–31, Jan. 2017, doi: 10.1016/j.media.2016.05.004.
R. Mehrotra, M. A. Ansari, R. Agrawal, and R. S. Anand, “A Transfer Learning approach for AI-based classification of brain tumors,” Machine Learning with Applications, vol. 2, p. 100003, Dec. 2020, doi: 10.1016/j.mlwa.2020.100003.
S. Liang et al., “Multimodal 3D DenseNet for IDH Genotype Prediction in Gliomas,” Genes, vol. 9, no. 8, p. 382, July 2018, doi: 10.3390/genes9080382.
A. Vidyarthi, R. Agarwal, D. Gupta, R. Sharma, D. Draheim, and P. Tiwari, “Machine Learning Assisted Methodology for Multiclass Classification of Malignant Brain Tumors,” IEEE Access, vol. 10, pp. 50624–50640, 2022, doi: 10.1109/access.2022.3172303.
Msoud Nickparvar, “Brain Tumor MRI Dataset.” Kaggle, 2021. doi: 10.34740/KAGGLE/DSV/2645886.
B. Hu, Z. Zhang, S. Chen, Q. Xu, and J. Li, “A metric for quantitative evaluation of glioma margin changes in magnetic resonance imaging,” Acta Radiol, vol. 65, no. 6, pp. 645–653, Mar. 2024, doi: 10.1177/02841851241229597.