Automated Segmentation of Intracranial Arteries on 4D Flow MRI for Hemodynamic Quantification

Accurate vessel segmentation is essential for reliable hemodynamic quantification in 4D Flow MRI. Automated segmentation with deep learning offers a promising alternative to the time-consuming, operator-dependent manual segmentation, but its application is often hindered by the scarcity of labeled datasets. Moreover, the impact on downstream hemodynamic quantification remains to be investigated. We developed a transfer learning-based intracranial artery segmentation model using a 3D full-resolution nnU-Net, pretrained on 355 TOF-MRA scans and fine-tuned on 11 7T 4D Flow MRI scans. The model was compared with two published models (U-Net and DenseNet U-Net) against the manual reference, evaluating segmentation metrics on test sets of different resolutions and hemodynamic quantification. The proposed nnU-Net achieved the highest Dice score (>0.85), the lowest HD95 ([~]3 mm), and the highest ICCs in cross-sectional area (0.62-0.87, except PCAs) and mean blood flow (0.78- 0.98). For wall shear stress (WSS) quantification, nnU-Net segmentations achieved the closest agreement with the manual reference (mean = 1.57 {+/-} 0.63 Pa, ICC = 0.96; max = 2.16 {+/-} 1.05 Pa, ICC = 0.97) and minimal bias ([&le;] 1.7%), whereas U-Net and DenseNet U-Net showed systematic under-(-5%) and overestimation (+7%), respectively. However, several vessel segments, including the ACA for DenseNet U-Net and the BA for U-Net, showed statistically significant differences (ANOVA post-hoc correction P < 0.05) in the flow-related metrics when compared with the manual reference. These results demonstrate that transfer learning with nnU-Net provides a robust, fully automated solution for intracranial artery analysis, and that segmentation accuracy directly affects 4D Flow MRI-derived hemodynamic quantification.