Usefulness of Monoenergetic Non-contrast CT and X-Map Images for Deep Learning-Based Stroke Lesion Segmentation

Vorberg L, Ditt H, Sühling M, Maier A, Murray N, Nicolaou S, Taubmann O (2025)

Publication Type: Conference contribution

Publication year: 2025

Journal

Lecture Notes in Computer Science Springer Verlag

Publisher: Springer

Edited Volumes: Image Analysis in Stroke Diagnosis and Interventions

Series: Lecture Notes in Computer Science

City/Town: Cham

Pages Range: 31-39

Conference Proceedings Title: Image Analysis in Stroke Diagnosis and Interventions

Event location: Marrakesh MA

ISBN: 9783031811005

DOI: 10.1007/978-3-031-81101-2_4

Abstract

This study investigates the usefulness of monoenergetic non-contrast computed tomography (NCCT) and x-map images in comparison to conventional NCCT for neural network-based stroke lesion segmentation. Utilizing the nnU-Net segmentation framework, models are trained on conventional, Mono+50, Mono+70, and Mono+120 NCCT as well as x-map images. Performance is evaluated on all image types, including those not seen during training, with the network predicting stroke core and hypoperfused volumes. Evaluation metrics include Dice scores and volumetric measurements. Results indicate that training nnU-Net with Mono+120 images on average yields the best performance across all tested image types. While x-map images, previously shown to facilitate lesion detection in human reader studies, do not outperform Mono+120 in same-domain training and testing, they demonstrate robust performance in inference for different energy level and conventional NCCT-trained models. For medium sized infarcts of 10–70 ml, the best Dice score is achieved when training with Mono+120 and testing on x-map images. These findings highlight the potential benefits of advanced spectral CT image derivatives for ischemic stroke segmentation.


Authors with CRIS profile

Linda Vorberg Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

Involved external institutions

Siemens Healthineers DE Germany (DE) University of British Columbia CA Canada (CA)

How to cite

APA:

Vorberg, L., Ditt, H., Sühling, M., Maier, A., Murray, N., Nicolaou, S., & Taubmann, O. (2025). Usefulness of Monoenergetic Non-contrast CT and X-Map Images for Deep Learning-Based Stroke Lesion Segmentation. In Ruisheng Su, Ezequiel de la Rosa, Leonhard Rist, Ewout Heylen, Frank te Nijenhuis, Danny Ruijters, Markus D. Schirmer, Richard McKinley, Susanne Wegener, Roland Wiest, Theo van Walsum (Eds.), Image Analysis in Stroke Diagnosis and Interventions (pp. 31-39). Marrakesh, MA: Cham: Springer.

MLA:

Vorberg, Linda, et al. "Usefulness of Monoenergetic Non-contrast CT and X-Map Images for Deep Learning-Based Stroke Lesion Segmentation." Proceedings of the 4th International Workshop, SWITCH 2024, and 6th International Challenge, ISLES 2024, Marrakesh Ed. Ruisheng Su, Ezequiel de la Rosa, Leonhard Rist, Ewout Heylen, Frank te Nijenhuis, Danny Ruijters, Markus D. Schirmer, Richard McKinley, Susanne Wegener, Roland Wiest, Theo van Walsum, Cham: Springer, 2025. 31-39.

BibTeX: Download