In EDS ansehen

Brain Stroke Classification Using CT Scans with Transformer-Based Models and Explainable AI

Gespeichert in:
Bibliographische Detailangaben
Titel: Brain Stroke Classification Using CT Scans with Transformer-Based Models and Explainable AI
Autoren: Shomukh Qari, Maha A. Thafar
Quelle: Diagnostics, Vol 15, Iss 19, p 2486 (2025)
Verlagsinformationen: MDPI AG, 2025.
Publikationsjahr: 2025
Bestand: LCC:Medicine (General)
Schlagwörter: hemorrhagic stroke, ischemic stroke, stroke classification, deep learning, transfer learning, vision transformer, Medicine (General), R5-920
Beschreibung: Background & Objective: Stroke remains a leading cause of mortality and long-term disability worldwide, demanding rapid and accurate diagnosis to improve patient outcomes. Computed tomography (CT) scans are widely used in emergency settings due to their speed, availability, and cost-effectiveness. This study proposes an artificial intelligence (AI)-based framework for multiclass stroke classification (ischemic, hemorrhagic, and no stroke) using CT scan images from the Ministry of Health of the Republic of Turkey. Methods: We adopted MaxViT, a state-of-the-art Vision Transformer (ViT)-based architecture, as the primary deep learning model for stroke classification. Additional transformer variants, including Vision Transformer (ViT), Transformer-in-Transformer (TNT), and ConvNeXt, were evaluated for comparison. To improve model generalization and handle class imbalance, classical data augmentation techniques were applied. Furthermore, explainable AI (XAI) was integrated using Grad-CAM++ to provide visual insights into model decisions. Results: The MaxViT model with augmentation achieved the highest performance, reaching an accuracy and F1-score of 98.00%, outperforming the baseline Vision Transformer and other evaluated models. Grad-CAM++ visualizations confirmed that the proposed framework effectively identified stroke-related regions, enhancing transparency and clinical trust. Conclusions: This research contributes to the development of a trustworthy AI-assisted diagnostic tool for stroke, facilitating its integration into clinical practice and improving access to timely and optimal stroke diagnosis in emergency departments.
Publikationsart: article
Dateibeschreibung: electronic resource
Sprache: English
ISSN: 2075-4418
Relation: https://www.mdpi.com/2075-4418/15/19/2486; https://doaj.org/toc/2075-4418
DOI: 10.3390/diagnostics15192486
Zugangs-URL: https://doaj.org/article/3540b028a4f042c999ca52d50ce69500
Dokumentencode: edsdoj.3540b028a4f042c999ca52d50ce69500
Datenbank: Directory of Open Access Journals
Beschreibung
Abstract:Background & Objective: Stroke remains a leading cause of mortality and long-term disability worldwide, demanding rapid and accurate diagnosis to improve patient outcomes. Computed tomography (CT) scans are widely used in emergency settings due to their speed, availability, and cost-effectiveness. This study proposes an artificial intelligence (AI)-based framework for multiclass stroke classification (ischemic, hemorrhagic, and no stroke) using CT scan images from the Ministry of Health of the Republic of Turkey. Methods: We adopted MaxViT, a state-of-the-art Vision Transformer (ViT)-based architecture, as the primary deep learning model for stroke classification. Additional transformer variants, including Vision Transformer (ViT), Transformer-in-Transformer (TNT), and ConvNeXt, were evaluated for comparison. To improve model generalization and handle class imbalance, classical data augmentation techniques were applied. Furthermore, explainable AI (XAI) was integrated using Grad-CAM++ to provide visual insights into model decisions. Results: The MaxViT model with augmentation achieved the highest performance, reaching an accuracy and F1-score of 98.00%, outperforming the baseline Vision Transformer and other evaluated models. Grad-CAM++ visualizations confirmed that the proposed framework effectively identified stroke-related regions, enhancing transparency and clinical trust. Conclusions: This research contributes to the development of a trustworthy AI-assisted diagnostic tool for stroke, facilitating its integration into clinical practice and improving access to timely and optimal stroke diagnosis in emergency departments.
ISSN:20754418
DOI:10.3390/diagnostics15192486