article · 2025

Brain Cancer Classification Using Topological Data Analysis and Machine Learning

Kacim Mohammad, Assaf Rabih, Mourad Oumar, Ghostine Christelle, Rammal Abbas

Cited by 0Abstract and details only

Abstract

Brain cancer is a life-threatening disease that necessitates accurate and early detection to improve patient outcomes. Magnetic Resonance Imaging (MRI) is the standard diagnostic technique for identifying brain tumors; however, manual interpretation by radiologists can be subjective, leading to inconsistencies in diagnosis. Recent advancements in Machine Learning (ML) have significantly improved tumor classification accuracy, but traditional methods often rely solely on pixel-based features, which may not fully capture the morphological complexity of tumors. This study explores the integration of Topological Data Analysis (TDA) with ML models to enhance brain tumor classification. Specifically, persistent homology, a core TDA technique, is leveraged to extract structural and geometric features from MRI scans, complementing conventional statistical features without the implication of any preprocessing technique. Four ML classifiers—Decision Tree, Naïve Bayes, Support Vector Machine (SVM), and Random Forest—were evaluated. The results demonstrate that incorporating topological features, and especially the novel use of persistent entropy, significantly enhances classification accuracy. The Random Forest classifier achieved the highest performance, with an accuracy of 98.12% and an AUC score of 0.9974. These findings suggest that TDA-based approaches provide valuable complementary information for tumor classification, paving the way for more robust and automated brain cancer detection systems.

Cite this paper

APA 7

Mohammad, K., Rabih, A., Oumar, M., Christelle, G., & Abbas, R. (2025). Brain Cancer Classification Using Topological Data Analysis and Machine Learning. https://doi.org/10.1109/etecom66111.2025.11319118

MLA 9

Mohammad, Kacim, et al. “Brain Cancer Classification Using Topological Data Analysis and Machine Learning.” 2025, pp. 1–6, https://doi.org/10.1109/etecom66111.2025.11319118.

Chicago

Mohammad, Kacim, Assaf Rabih, Mourad Oumar, Ghostine Christelle, and Rammal Abbas. 2025. “Brain Cancer Classification Using Topological Data Analysis and Machine Learning.” https://doi.org/10.1109/etecom66111.2025.11319118.

Harvard

Mohammad, K. et al. (2025) ‘Brain Cancer Classification Using Topological Data Analysis and Machine Learning’. Available at: https://doi.org/10.1109/etecom66111.2025.11319118.

BibTeX

@article{mohammad2025brain,
  title = {{Brain Cancer Classification Using Topological Data Analysis and Machine Learning}},
  author = {Mohammad, Kacim and Rabih, Assaf and Oumar, Mourad and Christelle, Ghostine and Abbas, Rammal},
  pages = {1--6},
  year = {2025},
  doi = {10.1109/etecom66111.2025.11319118}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.