Deep learning-based segmentation of abdominal aortic aneurysms and intraluminal thrombus in 3D ultrasound images
Medical & Biological Engineering & Computing · 2026
DOI: 10.1007/s11517-024-03216-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, 2026. Verfasst von Arjet Nievergeld und 5 weiteren Autor:innen. Beteiligte Einrichtung: PULS/e group, Department of Biomedical Engineering, Eindhoven University of Technology, De Rondom 70, 5612 AP, Eindhoven, The Netherlands. Hauptthemen laut MEDLINE: Aortic Aneurysm, Abdominal, Deep Learning, Thrombosis, Imaging, Three-Dimensional. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: e/MTIC.
Abstract (Originalsprache)
Ultrasound (US)-based patient-specific rupture risk analysis of abdominal aortic aneurysms (AAAs) has shown promising results. Input for these models is the patient-specific geometry of the AAA. However, segmentation of the intraluminal thrombus (ILT) remains challenging in US images due to the low ILT-blood contrast. This study aims to improve AAA and ILT segmentation in time-resolved three-dimensional (3D + t) US images using a deep learning approach. In this study a "no new net" (nnU-Net) model was trained on 3D + t US data using either US-based or (co-registered) computed tomography (CT)-based annotations. The optimal training strategy for this low-contrast data was determined for a limited dataset. The merit of augmentation was investigated, as well as the inclusion of low-contrast areas. Segmentation results were validated with CT-based geometries as the ground truth. The model trained on CT-based masks showed the best performance in terms of DICE index, Hausdorff distance, and diameter differences, covering a larger part of the AAA. With a higher accuracy and less manual input the model outperforms conventional methods, with a mean Hausdorff distance of 4.4 mm for the vessel and 7.8 mm for the lumen. However, visibility of the lumen-ILT interface remains the limiting factor, necessitating improvements in image acquisition to ensure broader patient inclusion and enable rupture risk assessment of AAAs in the future.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- PULS/e group, Department of Biomedical Engineering, Eindhoven University of Technology, De Rondom 70, 5612 AP, Eindhoven, The Netherlands.
- Department of Vascular Surgery, Catharina Hospital Eindhoven, Eindhoven, The Netherlands.
- Faculty of Science, Mathematics and Computer Science, Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands.
- Department of Biomedical Engineering and Physics, Amsterdam UMC, Amsterdam, The Netherlands.
- PULS/e group, Department of Biomedical Engineering, Eindhoven University of Technology, De Rondom 70, 5612 AP, Eindhoven, The Netherlands. r.lopata@tue.nl.
Förderung
- e/MTIC
Zitieren
APA
Nievergeld, A., Çetinkaya, B., Maas, E., van Sambeek, M., Lopata, R., & Awasthi, N. (2026). Deep learning-based segmentation of abdominal aortic aneurysms and intraluminal thrombus in 3D ultrasound images. Medical & Biological Engineering & Computing. https://doi.org/10.1007/s11517-024-03216-7
Vancouver
Nievergeld A, Çetinkaya B, Maas E, van Sambeek M, Lopata R, Awasthi N. Deep learning-based segmentation of abdominal aortic aneurysms and intraluminal thrombus in 3D ultrasound images. Medical & Biological Engineering & Computing. 2026. doi:10.1007/s11517-024-03216-7
BibTeX
@article{Nievergeld2026,
author = {Nievergeld, Arjet and Çetinkaya, Bünyamin and Maas, Esther and van Sambeek, Marc and Lopata, Richard and Awasthi, Navchetan},
title = {Deep learning-based segmentation of abdominal aortic aneurysms and intraluminal thrombus in 3D ultrasound images},
journal = {Medical & Biological Engineering & Computing},
year = {2026},
doi = {10.1007/s11517-024-03216-7}
}
EUVIMED