TumorXAI: Self-Supervised Deep Learning Framework for Explainable Brain MRI Tumor Classification

TL;DR

This paper demonstrates that self-supervised learning with ResNet-50 significantly improves brain tumor classification accuracy and interpretability on MRI data, especially with limited labels.

Contribution

It evaluates multiple SSL frameworks on MRI tumor classification, showing superior performance over supervised methods and integrating explainability techniques.

Findings

SimCLR achieved 99.64% accuracy and F1-score.

SSL models outperform supervised baselines with limited labels.

Explainability methods provide visual insights into model decisions.

Abstract

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.