Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition
9 May 2026 – 14 May 2026 · Cape Town, South Africa
468-03-005 ISMRM Abstract

CNN-based 4D Segmentation Improves Reproducibility of Hemodynamic Parameters in Aortic 4D Flow MRI

Primary: Analysis Methods - Segmentation and Detection
Secondary: Cardiovascular - Flow
468-03-005 · Segmentation for Cardiac Applications · Tuesday, 12 May, 1:40 PM–2:35 PM · Digital Posters Row I
Keywords: 4D flow MRI Aorta Hemodynamics Deep Learning Segmentation Bicuspid Aortic Valve
Accepted
Hinrich Rahlfs 1,2, Julio Garcia3, Markus Hüllebrand1,2,4,5, Sebastian Schmitter6, Sarah Nordmeyer7, Titus Kühne1,2, Heiko Stern8, Christian Meierhofer8, Andreas Harloff9, Sebastian Kelle2,10, Peter Bannas11, Jeanette Schulz-Menger12, Ralf F Trauzeddel12, Anja Hennemuth1,2,4,5
1Institute of Computer-assisted Cardiovascular Medicine, Deutsches Herzzentrum der Charité (DHZC), Berlin, Germany
2Charité-Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
3Stephenson Cardiac Imaging Centre, University of Calgary, Calgary, Canada
4Fraunhofer MEVIS, Bremen, Berlin, Germany
5Partner Site Berlin, DZHK (German Centre for Cardiovascular Research), Berlin, Germany
6Physikalisch-Technische Bundesanstalt (PTB), Braunschweig and Berlin, Berlin, Germany
7University Hospital Tuebingen - Diagnostic and Interventional Radiology, Tübingen, Germany
8Congenital Heart Disease and Pediatric Cardiology, German Heart Center Munich, Munich, Germany
9Department of Neurology and Neurophysiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
10Deutsches Herzzentrum der Charité (DHZC), Berlin, Germany
11Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
12ECRC Experimental and Clinical Research Center, Charité-Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
Presenting Author: Hinrich Rahlfs

Synopsis

Motivation:
Goals:
Approach:
Results:
Full abstract & presentation

The full text, figures, and any recorded presentation for this abstract are not shown here. Log in if you are a member or registered attendee with access.

Full abstracts, figures, and presentations for Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition are available to registered attendees. This content becomes freely available to the public roughly two years after the meeting.

To request or purchase access, contact the ISMRM Central Office at info@ismrm.org.

Log in

References

1. Ferdian, E., Dubowitz, D. J., Mauger, C. A., Wang, A., & Young, A. A. (2022). WSSNet: aortic wall shear stress estimation using deep learning on 4D flow MRI. Frontiers in cardiovascular medicine, 8, 769927. doi:10.3389/fcvm.2021.769927 [doi]
2. Manini, C., Hüllebrand, M., Walczak, L., Nordmeyer, S., Jarmatz, L., Kuehne, T., ... & Hennemuth, A. (2024). Impact of training data composition on the generalizability of convolutional neural network aortic cross-section segmentation in four-dimensional magnetic resonance flow imaging. Journal of Cardiovascular Magnetic Resonance, 26(2), 101081. doi:10.1016/j.jocmr.2024.101081 [doi]
3. Rahlfs, H., Brosig, J., Hüllebrand, M., Schmitter, S., Wamala, I., Kempfert, J., ... & Hennemuth, A. Learning 3D Lumen and Wall Segmentation in Vessel Trees from Centerline and Sparse Contour Annotations. doi:10.2139/ssrn.5564923 [doi]
4. Choy, C., Gwak, J., & Savarese, S. (2019). 4d spatio-temporal convnets: Minkowski convolutional neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 3075-3084). doi:10.1109/CVPR.2019.00319 [doi]
5. Gotkowski, K., Lüth, C., Jäger, P. F., Ziegler, S., Krämer, L., Denner, S., ... & Isensee, F. (2024). Embarrassingly simple scribble supervision for 3d medical segmentation. arXiv preprint arXiv:2403.12834. doi:10.48550/arXiv.2403.12834 [doi]
6. Trenti, C., Fedak, P. W., White, J. A., Garcia, J., & Dyverfeldt, P. (2024). Oscillatory shear stress is elevated in patients with bicuspid aortic valve and aortic regurgitation: a 4D flow cardiovascular magnetic resonance cross-sectional study. European Heart Journal-Cardiovascular Imaging, 25(3), 404-412. doi:10.1093/ehjci/jead283 [doi]

Cite this abstract

http://echo.ismrm.org/p/ISMRM2026/468-03-005