What type of study is this?

September 10, 2025Open Access

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

PLPengcheng LiPLA Information Engineering University YJYan JinUniversity of Southern California MWMonan WangHarbin University of Science and Technology

Key Points

SparseSwinMDT achieved an accuracy of 99.47% in classifying brain tumors, significantly improving upon existing methods.
The novel model integrates sparse token representation with multipath decision trees, optimizing performance on small datasets.
Using automated classification techniques, the model reduces computational complexity, making it viable for resource-constrained environments.
This research highlights the importance of early brain tumor classification to enhance treatment effectiveness.

Abstract

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.

问 AI

Bookmark

View Full Paper