Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Nov 9.
doi: 10.1002/mrm.70173. Online ahead of print.

ASL 4D MRA Intracranial Vessel Segmentation With Deep Learning U-Nets

Sang Hun Chung  1 , Zihan Wang  2 , Tianrui Zhao  1   3 , Zhitao Li  1 , Chase S Krumpelman  1 , Sarah J Moum  1   4 , Sameer A Ansari  1 , Lirong Yan  1   3
Affiliations

ASL 4D MRA Intracranial Vessel Segmentation With Deep Learning U-Nets

Sang Hun Chung et al. Magn Reson Med. .

Abstract

Purpose: To propose a spatio-temporal U-Net based network (4DST) that exploits both spatial and dynamic information while avoiding memory-intensive 4D convolutional layers for ASL-based non-contrast enhanced 4-dimensional MR angiography (4D MRA) vessel segmentation.

Methods: Pulsed ASL-based 4D MRA data were collected on 35 healthy volunteers and 5 arteriovenous malformation patients. Spatial only (2D, 3D) and spatio-temporal U-Net variations (including the proposed 4DST) were tested. Two recently developed methods, including feature-based isolation forest and BRAVE-Net, were used for comparison. Dice-Sørensen coefficient (DSC), center-line Dice (clDice), Hausdorff distance (HD), precision, accuracy, specificity, and sensitivity were calculated. Sensitivity was analyzed relative to SNR and arterial transit time (ATT) to explore detectability. From graph analysis, total vessel length, number of branches, and number of endpoints were reported.

Results: 4DST achieved the best DSC, clDice, and HD (0.876 ± 0.03, 0.865 ± 0.02, 6.241 ± 0.95, respectively). 4DST outperformed all other models across the SNR range of 1 to 10 and arterial transit time range of 500 to 800 ms in sensitivity. Last, the 4DST segmentations yielded total lengths and the number of branch splits that more closely matched the ground truths compared to the other models.

Conclusion: The proposed 4DST network architecture offers an overall improvement in 4D MRA vessel segmentation performance over the compared methods and provides the framework for an end-to-end trainable model for spatio-temporal datasets. Additionally, 4DST requires minimal pre/post-processing steps, rendering it an attractive solution for pulsed ASL-based 4D MRA vessel segmentation.

Keywords: 4D MRA; ASL; U‐net; arteriovenous malformation; deep learning; vessel segmentation.

PubMed Disclaimer

References

    1. L. Yan, S. Wang, Y. Zhuo, et al., “Unenhanced Dynamic MR Angiography: High Spatial and Temporal Resolution by Using True FISP–Based Spin Tagging With Alternating Radiofrequency,” Radiology 256, no. 1 (2010): 270–279.
    1. X. Bi, P. Weale, P. Schmitt, S. Zuehlsdorff, and R. Jerecic, “Non‐Contrast‐Enhanced Four‐Dimensional (4D) Intracranial MR Angiography: A Feasibility Study,” Magnetic Resonance in Medicine 63, no. 3 (2010): 835–841.
    1. J. Xu, D. Shi, C. Chen, et al., “Noncontrast‐Enhanced Four‐Dimensional MR Angiography for the Evaluation of Cerebral Arteriovenous Malformation: A Preliminary Trial,” Journal of Magnetic Resonance Imaging 34, no. 5 (2011): 1199–1205.
    1. F. Cong, Y. Zhuo, S. Yu, et al., “Noncontrast‐Enhanced Time‐Resolved 4D Dynamic Intracranial MR Angiography at 7T: A Feasibility Study,” Journal of Magnetic Resonance Imaging 48, no. 1 (2018): 111–120.
    1. S. Stojanović, A. Spasić, M. B. Nikolić, D. Kostić, M. Karać, and I. Turkalj, “Brain Arteriovenous Malformations,” Vojnosanitetski Pregled 76, no. 12 (2019): 1274–1283.

LinkOut - more resources