Explainable Deep Learning for Brain Tumor Classification: Comprehensive Benchmarking with Dual Interpretability and Lightweight Deployment

2025-11-20

AI Summary

To address the limited interpretability and poor deployability of deep learning models in brain MRI tumor classification, this paper proposes an end-to-end deep learning framework. Methodologically, it integrates dual interpretability mechanisms—Grad-CAM and GradientSHAP—to enhance clinical trustworthiness, and introduces a compact CNN with only 1.31M parameters to enable real-time inference (375 ms) on edge devices. Evaluated on public benchmarks, Inception-ResNet V2 achieves a test accuracy of 99.53% (all metrics >99.50%), while the lightweight CNN attains 96.49% accuracy with merely 1% of the parameters of mainstream models. The framework thus achieves a balanced trade-off among high accuracy, strong model interpretability, and cross-platform deployability—making it particularly suitable for resource-constrained primary healthcare settings.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Our study provides a full deep learning system for automated classification of brain tumors from MRI images, includes six benchmarked architectures (five ImageNet-pre-trained models (VGG-16, Inception V3, ResNet-50, Inception-ResNet V2, Xception) and a custom built, compact CNN (1.31M params)). The study moves the needle forward in a number of ways, including (1) full standardization of assessment with respect to preprocessing, training sets/protocols (optimizing networks with the AdamW optimizer, CosineAnnealingLR, patiene for early stopping = 7), and metrics to assess performance were identical along all models; (2) a high level of confidence in the localizations based on prior studies as both Grad-CAM and GradientShap explanation were used to establish anatomically important and meaningful attention regions and address the black-box issue; (3) a compact 1.31 million parameter CNN was developed that achieved 96.49% testing accuracy and was 100 times smaller than Inception-ResNet V2 while permitting real-time inference (375ms) on edge devices; (4) full evaluation beyond accuracy reporting based on measures of intersection over union, Hausdorff distance, and precision-recall curves, and confusion matrices across all splits. Inception-ResNet V2 reached state-of-the-art performance, achieving a 99.53% accuracy on testing and obtaining a precision, recall, and F1-score of at least 99.50% dominant performance based on metrics of recent studies. We demonstrated a lightweight model that is suitable to deploy on devices that do not have multi-GPU infrastructure in under-resourced settings. This end-to-end solution considers accuracy, interpretability, and deployability of trustworthy AI to create the framework necessary for performance assessment and deployment within advance and low-resource healthcare systems to an extent that enabled participation at the clinical screening and triage level.

Problem

• Automated brain tumor classification from MRI images using deep learning
• Addressing the black-box issue with dual interpretability methods for localization
• Developing lightweight models for deployment on resource-constrained edge devices

Innovation

• Benchmarks six deep learning models for brain tumor classification
• Uses Grad-CAM and GradientShap for dual interpretability of results
• Develops lightweight CNN for real-time edge device deployment