Comparative Evaluation of CNN and ResNet18 Architectures for MRI-Based Brain Tumor Classification Using Deep Learning

Abstract

Accurate and automated classification of brain tumors from magnetic resonance imaging (MRI) scans is essential for improving diagnostic precision and supporting clinical decision-making. This study presents a deep learning-based framework that employs two convolutional neural network architectures a custom-designed CNN and a pretrained ResNet18 model for multi-class classification of brain tumors using the publicly available Kaggle MRI dataset. The dataset was preprocessed through normalization, augmentation, and resizing to ensure consistency and model generalization. Both models were trained and evaluated using an 80:20 data split, and their performance was assessed based on accuracy, precision, recall, and F1-score metrics. Experimental results demonstrate that the ResNet18 model outperforms the baseline CNN, achieving a classification accuracy of 99.7%, precision of 99.5%, and F1-score of 99.6%. These results highlight the effectiveness of transfer learning and residual connections in improving feature representation and convergence speed. These findings underscore the effectiveness of transfer learning for medical image analysis and demonstrate the potential of deep learning"based methods for reliable, automated brain tumor diagnosis. Future research should focus on extending this work to 3D MRI volumes and integrating explainable AI techniques to enhance interpretability and clinical trust.

Accurate classification of brain tumors from Magnetic Resonance Imaging (MRI) is crucial for early diagnosis, treatment planning, and improving patient outcomes. However, manual interpretation of MRI scans is time-consuming and susceptible to diagnostic inconsistencies. This study presents a comparative evaluation of a custom Convolutional Neural Network (CNN) and a transfer learning"based ResNet18 model for automated brain tumor classification using the Kaggle Brain Tumor MRI Dataset, which includes four diagnostic categories: glioma, meningioma, pituitary tumor, and no tumor. Both models were trained and validated under identical preprocessing and experimental conditions to ensure fair comparison.

Comprehensive preprocessing, including normalization, augmentation, and stratified splitting (70% training, 20% validation, 10% testing), was applied to enhance data uniformity and generalization. The CNN model was trained from scratch, whereas the ResNet18 model is fine-tuned using pretrained ImageNet weights to leverage transfer learning. Performance was evaluated using accuracy, precision, recall, F1-score, and AUC metrics, supplemented by visual diagnostics such as confusion matrices, accuracy"loss curves, and F1-confidence plots.

The ResNet18 model achieved superior performance, with a test accuracy of 99.54%, precision of 0.98, recall of 0.99, F1-score of 0.99, and AUC of 0.992, outperforming the custom CNN, which attained 97.84% accuracy, precision of 0.94, recall of 0.95, F1-score of 0.94, and AUC of 0.975. Confusion matrix analysis indicated that both models accurately classified all tumor types, though minor misclassifications were observed between pituitary and no-tumor categories. ResNet18 exhibited faster convergence, smoother loss reduction, and greater robustness to intensity variations due to its residual connections and pretrained feature representations.