Zobrazit v EDS

An Explainable AI Framework for Stroke Classification Based on CT Brain Images

Uloženo v:
Podrobná bibliografie
Název: An Explainable AI Framework for Stroke Classification Based on CT Brain Images
Autoři: Serra Aksoy, Pinar Demircioglu, Ismail Bogrekci
Zdroj: AI, Vol 6, Iss 9, p 202 (2025)
Informace o vydavateli: MDPI AG, 2025.
Rok vydání: 2025
Sbírka: LCC:Electronic computers. Computer science
Témata: stroke classification, deep learning, explainable AI, XRAI, clinical decision support, CT imaging, Electronic computers. Computer science, QA75.5-76.95
Popis: Stroke is a major global cause of death and disability and necessitates both quick diagnosis and treatment within narrow windows of opportunity. CT scanning is still the first-line imaging in the acute phase, but correct interpretation may not always be readily available and may not be resource-available in poor and rural health systems. Automated stroke classification systems can offer useful diagnostic assistance, but clinical application demands high accuracy and explainable decision-making to maintain physician trust and patient safety. In this paper, a ResNet-18 model was trained on 6653 CT brain scans (hemorrhagic stroke, ischemia, normal) with two-phase fine-tuning and transfer learning, XRAI explainability analysis, and web-based clinical decision support system integration. The model performed with 95% test accuracy with good performance across all classes. This system has great potential for emergency rooms and resource-poor environments, offering quick stroke evaluation when specialists are not available, particularly by rapidly excluding hemorrhagic stroke and assisting in the identification of ischemic stroke, which are critical steps in considering tissue plasminogen activator (tPA) administration within therapeutic windows in eligible patients. The combination of classification, explainability, and clinical interface offers a complete framework for medical AI implementation.
Druh dokumentu: article
Popis souboru: electronic resource
Jazyk: English
ISSN: 2673-2688
Relation: https://www.mdpi.com/2673-2688/6/9/202; https://doaj.org/toc/2673-2688
DOI: 10.3390/ai6090202
Přístupová URL adresa: https://doaj.org/article/60cdcfa933d84d67971e17cc8f297c00
Přístupové číslo: edsdoj.60cdcfa933d84d67971e17cc8f297c00
Databáze: Directory of Open Access Journals
Popis
Abstrakt:Stroke is a major global cause of death and disability and necessitates both quick diagnosis and treatment within narrow windows of opportunity. CT scanning is still the first-line imaging in the acute phase, but correct interpretation may not always be readily available and may not be resource-available in poor and rural health systems. Automated stroke classification systems can offer useful diagnostic assistance, but clinical application demands high accuracy and explainable decision-making to maintain physician trust and patient safety. In this paper, a ResNet-18 model was trained on 6653 CT brain scans (hemorrhagic stroke, ischemia, normal) with two-phase fine-tuning and transfer learning, XRAI explainability analysis, and web-based clinical decision support system integration. The model performed with 95% test accuracy with good performance across all classes. This system has great potential for emergency rooms and resource-poor environments, offering quick stroke evaluation when specialists are not available, particularly by rapidly excluding hemorrhagic stroke and assisting in the identification of ischemic stroke, which are critical steps in considering tissue plasminogen activator (tPA) administration within therapeutic windows in eligible patients. The combination of classification, explainability, and clinical interface offers a complete framework for medical AI implementation.
ISSN:26732688
DOI:10.3390/ai6090202