EUVIMEDEUVIMED entdecken
Multizentrische StudieValidierungsstudieOpen Access · CC BY 4.0

The Role of Artificial Intelligence in Diagnosing Acute Ischemic Stroke Using Diffusion MRI: A Multicenter External Validation Study

Beyza Nur Kuzan, Ali Abbasian Ardakani, Mahmut Esat Aykan, Mustafa Demir, Servan Yaşar, Mehmet Semih Çakır, Afshin Mohammadi, Taha Yusuf Kuzan

Journal of Integrative Neuroscience · 21.04.2026 · 25 (4)

DOI: 10.31083/jin48811 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Journal of Integrative Neuroscience, online erschienen am 21.04.2026. Verfasst von Beyza Nur Kuzan und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Kartal Dr. Lütfi Kırdar City Hospital, 34865 Istanbul, Türkiye. Hauptthemen laut MEDLINE: Diffusion Magnetic Resonance Imaging, Ischemic Stroke, Deep Learning, Image Interpretation, Computer-Assisted. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Acute ischemic stroke is a time-sensitive medical emergency requiring rapid and accurate diagnosis to improve patient outcomes. While Diffusion-Weighted Imaging (DWI) on magnetic resonance imaging (MRI) is highly sensitive, artificial intelligence (AI) offers a potential solution to enhance diagnostic speed and accuracy. In this study we aimed to evaluate and externally validate a DWI-MRI-based deep learning model for automated stroke detection and compare its multicenter diagnostic performance with expert radiologists to determine generalizability and clinical utility.

Methods

This retrospective study involved 732 patient cases (acute ischemic stroke and non-stroke controls) from three different centers. A deep convolutional neural network (CNN) model was developed, trained, and internally validated using data from center 1 (n = 452 for training, n = 80 for validation). The model’s generalizability was then tested using independent external validation datasets from center 2 (n = 100) and center 3 (n = 100). The model’s diagnostic performance (sensitivity, specificity, accuracy, and area under the receiver operating characteristic (ROC) curve (AUC)) was systematically compared with that of three expert radiologists.

Results

The deep learning model demonstrated excellent diagnostic performance. In the internal validation, the model achieved 100% sensitivity, 100% specificity, and 100% accuracy (AUC = 1.000). Crucially, it maintained high performance on the external validation cohorts, achieving 100% sensitivity, 98% specificity, and 99% accuracy for both center 2 (AUC = 0.987) and center 3 (AUC = 0.986). This performance was comparable with the expert radiologists, who also achieved high accuracy across all datasets. Visualization techniques (gradient-weighted class activation map (Grad-CAM)) confirmed that the AI model focused on the correct pathological regions when making its classifications.

Conclusions

The DWI-MRI-based deep learning model provides high and reliable diagnostic accuracy for acute ischemic stroke, with performance comparable with that of expert radiologists. Its robust performance across multicenter data highlights its potential as a dependable decision-support tool in emergency departments, especially in settings with limited specialist availability, to facilitate faster and more consistent stroke diagnoses.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diffusion Magnetic Resonance ImagingIschemic StrokeDeep LearningImage Interpretation, Computer-AssistedArtificial IntelligenceNeuroimagingHumansRetrospective StudiesConvolutional Neural NetworksFemaleMaleAgedSensitivity and SpecificityMiddle AgedReproducibility of Results

Stichwörter der Autor:innen

artificial intelligencebrain ischemiacomputer-assisteddeep learningdiagnosisdiffusion magnetic resonance imaging

Autor:innen und Institutionen

  • Department of Radiology, Kartal Dr. Lütfi Kırdar City Hospital, 34865 Istanbul, Türkiye.
  • Department of Radiology Technology, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, 1971653313 Tehran, Iran.
  • Department of Radiology, Sancaktepe Şehit Prof. Dr. İlhan Varank Training and Research Hospital, University of Health Sciences, 34785 Istanbul, Türkiye.
  • Department of Radiology, Ümraniye Training and Research Hospital, 34764 Istanbul, Türkiye.
  • Department of Radiology, Faculty of Medicine, Istanbul University, 34093 Istanbul, Türkiye.
  • Department of Radiology, Faculty of Medicine, Urmia University of Medical Science, 5714783734 Urmia, Iran.

Zitieren

APA

Kuzan, B. N., Ardakani, A. A., Aykan, M. E., Demir, M., Yaşar, S., Çakır, M. S., Mohammadi, A., & Kuzan, T. Y. (2026). The Role of Artificial Intelligence in Diagnosing Acute Ischemic Stroke Using Diffusion MRI: A Multicenter External Validation Study. Journal of Integrative Neuroscience, 25(4). https://doi.org/10.31083/jin48811

Vancouver

Kuzan BN, Ardakani AA, Aykan ME, Demir M, Yaşar S, Çakır MS, et al. The Role of Artificial Intelligence in Diagnosing Acute Ischemic Stroke Using Diffusion MRI: A Multicenter External Validation Study. Journal of Integrative Neuroscience. 2026;25(4). doi:10.31083/jin48811

BibTeX
@article{Kuzan2026,
  author = {Kuzan, Beyza Nur and Ardakani, Ali Abbasian and Aykan, Mahmut Esat and Demir, Mustafa and Yaşar, Servan and Çakır, Mehmet Semih and Mohammadi, Afshin and Kuzan, Taha Yusuf},
  title = {The Role of Artificial Intelligence in Diagnosing Acute Ischemic Stroke Using Diffusion MRI: A Multicenter External Validation Study},
  journal = {Journal of Integrative Neuroscience},
  year = {2026},
  volume = {25},
  number = {4},
  doi = {10.31083/jin48811}
}
Kostenlos starten →