Bridging Vision and Graph Attention Learning Using Swin Transformer for Brain Tumor Classification

Abstract

Accurate brain tumor classification from MRI images is crucial for supporting clinical diagnosis. This study proposes a hybrid framework that integrates a Swin Transformer and Graph-based learning to enhance feature representation and relational modeling. The Swin Transformer, known for its linear computational complexity and multi-scale attention mechanism, serves as a hierarchical feature extractor. The Graph module, on the other hand, captures structural dependencies among the extracted features. The model is evaluated on a four-class brain MRI dataset using 5-Fold cross-validation. Experimental results consistently demonstrate high performance, with the best accuracy of 0.9907. The model achieves sensitivity and specificity of 0.9903 and 0.9970, respectively. Notably, all folds maintain accuracy above 0.9500, indicating strong robustness and generalization capability. The proposed approach effectively reduces misclassification across tumor categories and outperforms baseline methods, underscoring its potential for reliable brain tumor classification.