Transfer Learning and Explainable AI for Brain Tumor Classification: A Study Using MRI Data from Bangladesh

2024-12-14

2024 6th International Conference on Sustainable Technologies for Industry 5.0 (STI)

AI Summary

To address low diagnostic efficiency and accuracy in manual brain tumor identification in resource-constrained healthcare settings in Bangladesh, this study develops an automated three-class (glioma, meningioma, pituitary tumor) classification system trained exclusively on locally acquired, multi-center clinical MRI data. For the first time in Bangladesh, the framework systematically integrates transfer learning (using VGG16, VGG19, and ResNet50) with explainable AI techniques (Grad-CAM and Grad-CAM++) to jointly optimize classification performance and clinical interpretability. The VGG16-based model achieves 99.17% classification accuracy. Grad-CAM/++ significantly enhances lesion localization visualization, improving model decision transparency, robustness, and radiologist trust. This work establishes a reproducible, interpretable, and deployable technical paradigm for AI-assisted diagnosis in low-resource environments.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Brain tumors, regardless of being benign or ma-lignant, pose considerable health risks, with malignant tumors being more perilous due to their swift and uncontrolled prolifer-ation, resulting in malignancy. Timely identification is crucial for enhancing patient outcomes, particularly in nations such as Bangladesh, where healthcare infrastructure is constrained. Manual MRI analysis is arduous and susceptible to inaccuracies, rendering it inefficient for prompt diagnosis. This research sought to tackle these problems by creating an automated brain tumor classification system utilizing MRI data obtained from many hospitals in Bangladesh. Advanced deep learning models, including VGGI6, VGGI9, and ResNet50, were utilized to classify glioma, meningioma, and various brain cancers. Explainable AI (XAI) methodologies, such as Grad-CAM and Grad-CAM++, were employed to improve model interpretability by emphasizing the critical areas in MRI scans that influenced the categorization. VGG16 achieved the most accuracy, attaining 99.17%. The integration of XAI enhanced the system's transparency and stability, rendering it more appropriate for clinical application in resource-limited environments such as Bangladesh. This study highlights the capability of deep learning models, in conjunction with explainable artificial intelligence (XAI), to enhance brain tumor detection and identification in areas with restricted access to advanced medical technologies.

Problem

• Automated brain tumor classification using MRI data in Bangladesh
• Improving diagnosis accuracy with deep learning models like VGG16 and ResNet50
• Enhancing model interpretability via Explainable AI (XAI) for clinical use

Innovation

• Transfer learning with VGG16, VGG19, ResNet50 models
• Explainable AI using Grad-CAM and Grad-CAM++
• Automated MRI classification for brain tumors