EUVIMEDEUVIMED entdecken
Crossref

An Artificial Intelligence-Based Screening Tool for Detection of Cerebral Venous Thrombosis on Non-Contrast Brain CT

Ali Namjoo-Moghadam, Ali Mobaien, Zahra Bayat, Saba Nouri, Nahid Abolpour, Marzieh Salimi, Etrat Hooshmandi, Razieh Sadat Mousavi-Roknabadi, Nima Fadakar, Maryam Poursadeghfard, Vahid Reza Ostovan, Abdolkhalegh Keshavarzi und 3 weitere

Cerebrovascular Diseases · 20.04.2026 · 1-9

DOI: 10.1159/000551860 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cerebrovascular Diseases, online erschienen am 20.04.2026. Verfasst von Ali Namjoo-Moghadam und 14 weiteren Autor:innen. Beteiligte Einrichtung: AI Clinical Lab and Biological Data Bank, Shiraz University of Medical Sciences, Shiraz, Iran. Die Arbeit nennt 20 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

While non-contrast computed tomography (NCCT) is the primary imaging modality in emergency settings, it has a low sensitivity for detection of cerebral venous thrombosis (CVT). This study aimed to develop an artificial intelligence (AI) tool to screen for CVT on routine NCCT scans.

Methods

We used a retrospectively collected dataset of 692 patients, including 258 with CVT from Iran Cerebral Venous Thrombosis Registry (ICVTR) (code: 9001013381) and 434 controls. NCCT images were processed using the pretrained CT foundation model to generate high-dimensional embeddings. These embeddings were used to train several machine learning classifiers: support vector machine (SVM) with linear, polynomial, and radial basis function kernels, logistic regression, random forest, an artificial neural network, and a soft voting ensemble model. Model performance was assessed using a 10-fold cross-validation protocol.

Results

The random forest model achieved the highest specificity of 0.856 ± 0.050, excelling at identifying non-CVT cases. Conversely, the ensemble model yielded the highest sensitivity of 0.614 ± 0.087. The SVM with a linear kernel provided the best overall discriminative ability, with the highest area under the receiver operating characteristic curve of 0.718 ± 0.053. No single model demonstrated superiority across all metrics, reflecting the inherent challenge of detecting CVT on NCCT.

Conclusion

Our findings demonstrate the feasibility of using an AI-based model to detect CVT on non-contrast CT scans. While not yet a replacement for expert radiological interpretation, this approach serves as a promising automated screening tool. It has the potential to reduce diagnostic delays and improve patient outcomes by flagging suspicious cases in emergency workflows.

Schlagwörter

Stichwörter der Autor:innen

Artificial intelligenceCerebral venous thrombosisComputed tomographyMachine learningNeuroimaging

Autor:innen und Institutionen

  • AI Clinical Lab and Biological Data Bank, Shiraz University of Medical Sciences, Shiraz, Iran.
  • Clinical Neurology Research Center, Shiraz University of Medical Sciences, Shiraz, Iran.
  • Emergency Medicine Department, Shiraz University of Medical Sciences, Shiraz, Iran.
  • Department of AI in Medical Sciences, Shiraz University of Medical Sciences, Shiraz, Iran.
  • Department of Community Medicine, Shiraz University of Medical Sciences, Shiraz, Iran.
  • Allergy Research Center, Shiraz University of Medical Sciences, Shiraz, Iran.

Zitieren

APA

Namjoo-Moghadam, A., Mobaien, A., Bayat, Z., Nouri, S., Abolpour, N., Salimi, M., Hooshmandi, E., Mousavi-Roknabadi, R. S., Fadakar, N., Poursadeghfard, M., Ostovan, V. R., Keshavarzi, A., Lotfi, M., Sharifi, M., & Borhani-Haghighi, A. (2026). An Artificial Intelligence-Based Screening Tool for Detection of Cerebral Venous Thrombosis on Non-Contrast Brain CT. Cerebrovascular Diseases, 1-9. https://doi.org/10.1159/000551860

Vancouver

Namjoo-Moghadam A, Mobaien A, Bayat Z, Nouri S, Abolpour N, Salimi M, et al. An Artificial Intelligence-Based Screening Tool for Detection of Cerebral Venous Thrombosis on Non-Contrast Brain CT. Cerebrovascular Diseases. 2026:1-9. doi:10.1159/000551860

BibTeX
@article{NamjooMoghadam2026,
  author = {Namjoo-Moghadam, Ali and Mobaien, Ali and Bayat, Zahra and Nouri, Saba and Abolpour, Nahid and Salimi, Marzieh and Hooshmandi, Etrat and Mousavi-Roknabadi, Razieh Sadat and Fadakar, Nima and Poursadeghfard, Maryam and Ostovan, Vahid Reza and Keshavarzi, Abdolkhalegh and Lotfi, Mehrzad and Sharifi, Mehrdad and Borhani-Haghighi, Afshin},
  title = {An Artificial Intelligence-Based Screening Tool for Detection of Cerebral Venous Thrombosis on Non-Contrast Brain CT},
  journal = {Cerebrovascular Diseases},
  year = {2026},
  pages = {1--9},
  doi = {10.1159/000551860}
}
Kostenlos starten →