TumorXAI: Self-Supervised Deep Learning Framework for Explainable Brain MRI Tumor Classification
For medical imaging researchers, this demonstrates SSL's effectiveness for brain tumor classification with limited annotations, but the results are on a single public dataset with near-perfect scores, suggesting potential overfitting or data leakage.
The paper applies self-supervised learning (SSL) frameworks (SimCLR, BYOL, DINO, MoCo v3) to classify 17 brain tumor types from 4,448 MRIs, achieving 99.64% accuracy with SimCLR. SSL pretraining outperforms supervised baselines when labels are limited, and explainable AI techniques enhance interpretability.
Classifying brain tumors using magnetic resonance imaging (MRI) is crucial for early diagnosis and treatment; however, tumor heterogeneity and a dearth of annotated datasets restrict the use of supervised deep learning approaches. In this work, we use self-supervised learning (SSL) to study multi-class brain tumor classification. Using a ResNet-50 backbone, we evaluate four SSL frameworks including SimCLR, BYOL, DINO, and Moco v3 on a publicly available dataset of 4,448 MRIs with 17 distinct tumor types. On the dataset, SimCLR achieved 99.64% accuracy, 99.64% precision, 99.64% recall, and 99.64% F1-score. The workflow includes preprocessing, fine-tuning, linear evaluation, and SSL pretraining with data augmentations. Results show that, when labels are limited, SSL-pretrained models outperform supervised baselines in terms of F1-score, recall, accuracy, and precision. Additionally, by providing visual insights into model decisions, Explainable AI techniques (Grad-CAM, Grad-CAM++, EigenCAM) enhance interpretability. These results demonstrate SSL's scalability and dependability in diagnosing brain tumors from unlabeled medical data.