Enhancing MRI-Based Brain Tumor Detection with Blockchain-Integrated Deep Learning Models: A Performance Evaluation

Abstract

Accurate and rapid diagnosis of brain tumors is crucial for patient survival and effective treatment planning. Leveraging AI in medical diagnostics, particularly deep learning (DL) models for analyzing MRI data, significantly enhances accuracy in brain tumor detection. In this study, we build on the work of Banik et al. (2024), who introduced BrainTumorNet—a CNN integrated with blockchain technology to ensure data security and traceability in MRI-based brain tumor diagnostics. We present a comparative analysis between BrainTumorNet and an alternative deep learning-based diagnostic framework that utilizes a hybrid ResNet-Inception architecture without blockchain support. Both systems are evaluated across standard datasets using multiple performance metrics, including accuracy, recall, and f1-score. Our findings illustrate the benefits of blockchain integration for secure data management and the effectiveness of CNN architectures in medical imaging tasks.