CE-RS-SBCIT A Novel Channel Enhanced Hybrid CNN Transformer with Residual, Spatial, and Boundary-Aware Learning for Brain Tumor MRI Analysis

TL;DR

This paper introduces CE-RS-SBCIT, a hybrid CNN-Transformer framework with residual, spatial, and boundary-aware modules for improved brain tumor MRI classification, addressing challenges like heterogeneity and contrast sensitivity.

Contribution

The paper proposes a novel hybrid CNN-Transformer model with channel enhancement and spatial attention, improving feature extraction and classification accuracy in brain tumor MRI analysis.

Findings

Achieved 98.30% accuracy on MRI datasets.

Demonstrated superior sensitivity and precision over existing methods.

Effectively handled heterogeneity and contrast variations in MRI data.

Abstract

Brain tumors remain among the most lethal human diseases, where early detection and accurate classification are critical for effective diagnosis and treatment planning. Although deep learning-based computer-aided diagnostic (CADx) systems have shown remarkable progress. However, conventional convolutional neural networks (CNNs) and Transformers face persistent challenges, including high computational cost, sensitivity to minor contrast variations, structural heterogeneity, and texture inconsistencies in MRI data. Therefore, a novel hybrid framework, CE-RS-SBCIT, is introduced, integrating residual and spatial learning-based CNNs with transformer-driven modules. The proposed framework exploits local fine-grained and global contextual cues through four core innovations: (i) a smoothing and boundary-based CNN-integrated Transformer (SBCIT), (ii) tailored residual and spatial learning CNNs, (iii) a channel enhancement (CE) strategy, and (iv) a novel spatial attention mechanism. The developed SBCIT employs stem convolution and contextual interaction transformer blocks with systematic smoothing and boundary operations, enabling efficient global feature modeling. Moreover, Residual and spatial CNNs, enhanced by auxiliary transfer-learned feature maps, enrich the representation space, while the CE module amplifies discriminative channels and mitigates redundancy. Furthermore, the spatial attention mechanism selectively emphasizes subtle contrast and textural variations across tumor classes. Extensive evaluation on challenging MRI datasets from Kaggle and Figshare, encompassing glioma, meningioma, pituitary tumors, and healthy controls, demonstrates superior performance, achieving 98.30% accuracy, 98.08% sensitivity, 98.25% F1-score, and 98.43% precision.