Thrombus Detection in Non-Contrast Head CT using Graph Deep Learning

Popp A, Taubmann O, Thamm F, Ditt H, Maier A, Breininger K (2022)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2022

Conference Proceedings Title: Bildverarbeitung in der Medizin

Event location: Heidelberg

DOI: 10.1007/978-3-658-36932-3_33


In case of an acute ischemic stroke, rapid diagnosis and removal of the occluding thrombus (blood clot) are crucial for a successful recovery. We present an automated thrombus detection system for noncontrast computed tomography (NCCT) images to improve the clinical workflow, where NCCT is typically acquired as a first-line imaging tool to identify the type of the stroke. The system consists of a candidate detection model and a subsequent classification model. The detection model generates a volumetric heatmap from the NCCT and extracts multiple potential clot candidates, sorted by their likeliness in descending order. The classification model performs reprioritization of these candidates using graph-based deep learning methods, where the candidates are no longer considered independently, but in a global context. It was optimized to classify the candidates as clot or no clot. The candidate detection model, which also serves as a baseline, yields a ROC AUC of 79.8%, which could be improved to 85.2% by the proposed graph-based classification model.

Authors with CRIS profile

Involved external institutions

How to cite


Popp, A., Taubmann, O., Thamm, F., Ditt, H., Maier, A., & Breininger, K. (2022). Thrombus Detection in Non-Contrast Head CT using Graph Deep Learning. In Bildverarbeitung in der Medizin. Heidelberg.


Popp, Antonia, et al. "Thrombus Detection in Non-Contrast Head CT using Graph Deep Learning." Proceedings of the Bildverarbeitung in der Medizin 2022, Heidelberg 2022.

BibTeX: Download