Brain Stroke Detection and Classification Using CT Imaging with Transformer Models and Explainable AI

2025-07-13

AI Summary

Stroke is a leading cause of global mortality, necessitating rapid, accurate, and interpretable CT-based diagnosis in emergency settings. To address this, we propose a vision Transformer–based multi-class classification framework for automated differentiation among ischemic stroke, hemorrhagic stroke, and non-stroke cases. Our method innovatively integrates the MaxViT backbone with Grad-CAM++ for pixel-level interpretability, enhancing clinical trustworthiness without compromising performance. We further improve generalizability via comprehensive data augmentation and synthetic CT image generation. Experimental results on a clinical CT dataset demonstrate that the optimized MaxViT model achieves 98.00% accuracy and F1-score—significantly outperforming established baseline models (e.g., ResNet-50, ViT-B/16). This work delivers an end-to-end, high-accuracy, and clinically interpretable AI solution for acute stroke triage in emergency departments.

Technology Category

Computer Vision: Interpretability, Explainability, and TransparencyMachine Learning: Transparent, Interpretable, Explainable MLKnowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAGSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsResponsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Stroke is one of the leading causes of death globally, making early and accurate diagnosis essential for improving patient outcomes, particularly in emergency settings where timely intervention is critical. CT scans are the key imaging modality because of their speed, accessibility, and cost-effectiveness. This study proposed an artificial intelligence framework for multiclass stroke classification (ischemic, hemorrhagic, and no stroke) using CT scan images from a dataset provided by the Republic of Turkey's Ministry of Health. The proposed method adopted MaxViT, a state-of-the-art Vision Transformer, as the primary deep learning model for image-based stroke classification, with additional transformer variants (vision transformer, transformer-in-transformer, and ConvNext). To enhance model generalization and address class imbalance, we applied data augmentation techniques, including synthetic image generation. The MaxViT model trained with augmentation achieved the best performance, reaching an accuracy and F1-score of 98.00%, outperforming all other evaluated models and the baseline methods. The primary goal of this study was to distinguish between stroke types with high accuracy while addressing crucial issues of transparency and trust in artificial intelligence models. To achieve this, Explainable Artificial Intelligence (XAI) was integrated into the framework, particularly Grad-CAM++. It provides visual explanations of the model's decisions by highlighting relevant stroke regions in the CT scans and establishing an accurate, interpretable, and clinically applicable solution for early stroke detection. This research contributed to the development of a trustworthy AI-assisted diagnostic tool for stroke, facilitating its integration into clinical practice and enhancing access to timely and optimal stroke diagnosis in emergency departments, thereby saving more lives.

Problem

• Detect and classify stroke types using CT imaging
• Improve accuracy and transparency in AI diagnosis
• Enhance early stroke detection for emergency care

Innovation

• MaxViT transformer for stroke classification
• Data augmentation with synthetic images
• Explainable AI using Grad-CAM++