What question did this study set out to answer?

This research evaluates the effectiveness of CNNs versus a Swin-Tiny Transformer in classifying brain tumors from MRI data.

June 9, 2026Open Access

Comparative evaluation of convolutional neural networks and Swin transformer for multiclass brain tumor MRI classification

Key Points

This research evaluates the effectiveness of CNNs versus a Swin-Tiny Transformer in classifying brain tumors from MRI data.
Used Brain Tumor MRI dataset (7,023 slices) and BRISC-2025 dataset (6,000 slices) for training and validation.
Implemented image normalization and spatial augmentation; addressed class imbalance with weighted cross-entropy loss.
Trained Pure CNN, Res-CNN, and Swin-Tiny Transformer using fivefold stratified cross-validation and evaluated accuracy, precision, recall, and AUC.
The Swin-Tiny Transformer achieved an accuracy of 99.01% and an F1-score of 99.01% on internal testing.
The Res-CNN reached 60.95% accuracy; Pure CNN recorded 58.73% accuracy, with both models misclassifying glioma and pituitary slices.
External validation on the BRISC-2025 dataset resulted in 97.55% accuracy for the Swin-Tiny Transformer, showing robust generalization.

Abstract

Accurate brain tumor diagnosis depends on reliable MRI classification. Manual interpretation is time-consuming and depends on the reader’s experience, so automated methods are favored. CNNs perform well in medical imaging but struggle with long-range context, while transformers, using self-attention, model global dependencies and have shown success in neuroimaging. This study compares CNNs and a Swin-Tiny Transformer for classifying brain tumors from contrast-enhanced T1 MRI slices, using internal and external tests to evaluate generalization. We used the publicly available Brain Tumor MRI dataset (7,023 axial T1-CE slices; four classes: glioma, meningioma, pituitary tumor, and no tumor) as the internal dataset and the BRISC-2025 dataset (6,000 slices with the same four labels) for external validation. All images were converted to 3-channel 224 × 224 inputs, normalized, and augmented with spatial transformations; class imbalance was addressed using inverse-frequency class-weighted cross-entropy loss. A custom Pure CNN, a residual CNN (Res-CNN), and a Swin-Tiny Transformer were trained with the AdamW optimizer and evaluated using accuracy, precision, recall, F1-score, macro-AUC, confusion matrices, fivefold stratified cross-validation on the internal dataset, and external testing on the BRISC-2025 dataset. On the internal test split, the Pure CNN achieved 58.73% accuracy (F1-score 57.11%, macro-AUC 0.9092), and the Res-CNN achieved 60.95% accuracy (F1-score 57.02%, macro-AUC 0.8988), with both models frequently misclassifying glioma and pituitary slices. In contrast, the Swin-Tiny Transformer achieved 99.01% test accuracy, an overall F1-score of 99.01%, and a macro-AUC of 0.9997, with only minimal residual errors, predominantly involving glioma–meningioma confusion. Five-fold cross-validation yielded a mean Swin-Tiny accuracy of 99.33% ± 0.17 (macro-AUC 0.9997), and external evaluation on BRISC-2025, without fine-tuning, resulted in 97.55% accuracy and a macro-AUC of 0.9993, indicating robust generalization across datasets acquired with different imaging characteristics. The Swin-Tiny Transformer substantially outperformed the custom CNN baselines, delivering very high internal and strong external accuracy with well-balanced per-class metrics in 4-class brain tumor MRI classification. These findings suggest that Swin-based architectures have considerable potential as robust decision-support tools for brain tumor imaging, although the slice-level nature of public datasets, absence of patient-level stratification, and higher computational cost of transformer models highlight the need for patient-level, multimodal, and prospective validation before routine clinical deployment.

KI fragen

Bookmark

View Full Paper