Sparse transformer and multipath decision tree: a novel approach for efficient brain tumor classification

• Published in: Scientific reports Vol. 15; no. 1; pp. 28915 - 14
• Main Authors: Li, Pengcheng, Jin, Yuqi, Wang, Monan, Liu, Fengjie
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 07.08.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705/1042; 692/4028/67/2321; Accuracy; Algorithms; Brain cancer; Brain Neoplasms - classification; Brain Neoplasms - diagnosis; Brain Neoplasms - diagnostic imaging; Brain Neoplasms - pathology; Brain research; Brain tumors; Classification; Classification of brain tumors; Datasets; Decision Trees; Glioma; Humanities and Social Sciences; Humans; Image Processing, Computer-Assisted - methods; Magnetic resonance imaging; Medical imaging; Medical technology; multidisciplinary; Multipath decision tree; Neural networks; Neuroimaging; Science; Science (multidisciplinary); Semantics; Sparse transformer; Swin transformer; Tumors; Swin transformer; Sparse transformer; Classification of brain tumors; Multipath decision tree
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-025-13115-y

Early classification of brain tumors is the key to effective treatment. With advances in medical imaging technology, automated classification algorithms face challenges due to tumor diversity. Although Swin Transformer is effective in handling high-resolution images, it encounters difficulties with small datasets and high computational complexity. This study introduces SparseSwinMDT, a novel model that combines sparse token representation with multipath decision trees. Experimental results show that SparseSwinMDT achieves an accuracy of 99.47% in brain tumor classification, significantly outperforming existing methods while reducing computation time, making it particularly suitable for resource-constrained medical environments.