{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/brain-tumour-classification-using-bof-surf","title":"Brain tumour classification using BoF-SURF with filter-based feature selection methods","arxiv_id":null,"date":"2024-01-19","proceeding":"Multimedia Tools and Applications 2024 1","authors":["Zhana Fidakar Mohammed","Diyari Jalal Mussa"],"abstract":"Currently, cancer is a global concern with a focus on reducing its incidence and advancing diagnostic techniques. Faster and more precise cancer cell detection improves treatment and survival prospects. The objective of this study is to effectively categorize brain tumors with a specific focus on three types: meningioma, glioma, and pituitary tumors. The research adopts a thorough methodology encompassing pre-processing, feature extraction, feature selection, and classification using various techniques such as k-nearest neighbor (kNN), support vector machine (SVM), and Ensemble methods. Features were extracted using the bag of features- speeded-up robust features (BoF-SURF) algorithm for different cluster sizes (500, 250, 375, 750, and 825). Diverse feature selection algorithms, including ReliefF, analysis of variance (ANOVA), Kruskal Wallis, maximum relevance minimum redundancy (MRMR), and chi-square (CHI2), were employed to enhance detection accuracy. The proposed method, assessed on a public dataset comprising 3064 MRI scans of malignant brain tumours. The results of our experiments strongly support the effectiveness of our proposed method, achieving an impressive accuracy rate of 98.7%. Additionally, remarkable values of 98.4%, 98.5%, and 98.6% have been obtained for sensitivity, precision, and F1-score, respectively, when using the kNN classifier with 512 features selected from a cluster size of 750 using the ReliefF method. These outcomes clearly outperform existing approaches.","url_abs":"https://link.springer.com/article/10.1007/s11042-024-18171-6#Abs1","url_pdf":"https://link.springer.com/content/pdf/10.1007/s11042-024-18171-6.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"brain-tumour-classification-using-bof-surf","repo_url":"https://github.com/diyari-mussa/Brain-Tumour-Classification-using-BoF-SURF","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"cell-detection","task_name":"Cell Detection"},{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"tumour-classification","task_name":"Tumour Classification"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[{"method_slug":"feature-selection","method_name":"Feature Selection"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}