# Automatic Segmentation, Feature Extraction and Comparison of Healthy and Stroke Cerebral Vasculature

arXiv: https://arxiv.org/abs/2002.11208 · HTML: https://mlsanity.com/paper/2002.11208/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2020.

## Built on by (most cited first, 7 of 7)

- [vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation](https://mlsanity.com/paper/2411.17386/) (2024)
- [Deep Learning for Vascular Segmentation and Applications in Phase Contrast Tomography Imaging](https://mlsanity.com/paper/2311.13319/) (2023)
- [Physics-informed neural networks for improving cerebral hemodynamics predictions](https://mlsanity.com/paper/2108.11498/) (2021)
- [Segmentation method for cerebral blood vessels from MRA using hysteresis](https://mlsanity.com/paper/2303.05113/) (2023)
- [Reconstructing Blood Flow in Data-Poor Regimes: A Vasculature Network Kernel for Gaussian Process Regression](https://mlsanity.com/paper/2403.09758/) (2024)
- [SWinMamba: Serpentine Window State Space Model for Vascular Segmentation](https://mlsanity.com/paper/2507.01323/) (2025)
- [StrokeNeXt: A Siamese-encoder Approach for Brain Stroke Classification in Computed Tomography Imagery](https://mlsanity.com/paper/2602.15087/) (2026)

## Abstract (arXiv)

Accurate segmentation of cerebral vasculature and a quantitative assessment of cerebrovascular morphology is critical to various diagnostic and therapeutic purposes and is pertinent to studying brain health and disease. However, this is still a challenging task due to the complexity of the vascular imaging data. We propose an automated method for cerebral vascular segmentation without the need of any manual intervention as well as a method to skeletonize the binary volume to extract vascular geometric features which can characterize vessel structure. We combine a probabilistic vessel-enhancing filtering with an active-contour technique to segment magnetic resonance and computed tomography angiograms (MRA and CTA) and subsequently extract the vessel centerlines and diameters to calculate the geometrical properties of the vasculature. Our method was validated using a 3D phantom of the Circle-of-Willis region with 84% mean Dice Similarity and 85% mean Pearson Correlation with minimal modified Hausdorff distance error. We applied this method to a dataset of healthy subjects and stroke patients and present a quantitative comparison between them. We found significant differences in the geometric features including total length (2.88 +/- 0.38 m for healthy and 2.20 +/- 0.67 m for stroke), volume (40.18 +/- 25.55 ml for healthy and 34.43 +/- 21.83 ml for stroke), tortuosity (3.24 +/- 0.88 rad/cm for healthy and 5.80 +/- 0.92 rad/cm for stroke) and fractality (box dimension 1.36 +/- 0.28 for healthy vs. 1.69 +/- 0.20 for stroke). This technique can be applied on any imaging modality and can be used in the future to automatically obtain the 3D segmented vasculature for diagnosis and treatment planning of Stroke and other cerebrovascular diseases (CVD) in the clinic and also to study the morphological changes caused by various CVD.