Vorberg L, Taubmann O, Ditt H, Maier A (2024)
Publication Type: Conference contribution
Publication year: 2024
Publisher: Springer Science and Business Media Deutschland GmbH
Pages Range: 267-272
Conference Proceedings Title: Informatik aktuell
Event location: Erlangen, DEU
ISBN: 9783658440367
DOI: 10.1007/978-3-658-44037-4_72
In stroke diagnosis, a non-contrast CT (NCCT) is the first scan acquired and bears the possibility to identify ischemic changes in the brain. Their identification and segmentation are subject to high inter-rater variability. We develop and evaluate models based on labels that reflect the uncertainty in segmentation hypotheses by annotation of minimum (“inner”) and maximum (“outer”) contours of perceived presence of infarct core and hypoperfused tissue. These labels are used for training nnU-Net to segment both from NCCT and CT angiography (CTA) scans of 167 patients. The predicted output is post-processed to obtain delineations of the tissue of interest at varying distances between inner and outer contours. Compared to the ground truth, infarcts of medium size (10 to 70 ml) could be segmented in the NCCT scans with a median error of 3.7 ml (6.2 ml for CTA) of excess predicted volume, missing 6.4 ml (3.5 ml) of the infarct.
APA:
Vorberg, L., Taubmann, O., Ditt, H., & Maier, A. (2024). Segmentation of Acute Ischemic Stroke in Native and Enhanced CT using Uncertainty-aware Labels. In Andreas Maier, Thomas M. Deserno, Heinz Handels, Klaus Maier-Hein, Christoph Palm, Thomas Tolxdorff (Eds.), Informatik aktuell (pp. 267-272). Erlangen, DEU: Springer Science and Business Media Deutschland GmbH.
MLA:
Vorberg, Linda, et al. "Segmentation of Acute Ischemic Stroke in Native and Enhanced CT using Uncertainty-aware Labels." Proceedings of the German Conference on Medical Image Computing, BVM 2024, Erlangen, DEU Ed. Andreas Maier, Thomas M. Deserno, Heinz Handels, Klaus Maier-Hein, Christoph Palm, Thomas Tolxdorff, Springer Science and Business Media Deutschland GmbH, 2024. 267-272.
BibTeX: Download