Neural Vessel Segmentation and Gaussian Splatting for 3D Reconstruction of Cerebral Angiography

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F26%3A0200945" target="_blank" >RIV/00216305:26220/26:0200945 - isvavai.cz</a>

Result on the web

<a href="https://www.mdpi.com/2673-2688/7/1/22" target="_blank" >https://www.mdpi.com/2673-2688/7/1/22</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/ai7010022" target="_blank" >10.3390/ai7010022</a>

Result language

angličtina

Original language name

Neural Vessel Segmentation and Gaussian Splatting for 3D Reconstruction of Cerebral Angiography

Original language description

Cerebrovascular diseases are a leading cause of global mortality, underscoring the need for objective and quantitative 3D visualization of cerebral vasculature from dynamic imaging modalities. Conventional analysis is often labor-intensive, subjective, and prone to errors due to image noise and subtraction artifacts. This study tackles the challenge of achieving fast and accurate volumetric reconstruction from angiography sequences. We propose a multi-stage pipeline that begins with image restoration to enhance input quality, followed by neural segmentation to extract vascular structures. Camera poses and sparse geometry are estimated through Structure-from-Motion, and these reconstructions are refined by leveraging the segmentation maps to isolate vessel-specific features. The resulting data are then used to initialize and optimize a 3D Gaussian Splatting model, enabling anatomically precise representation of cerebral vasculature. The integration of deep neural segmentation priors with explicit geometric initialization yields highly detailed 3D reconstructions of cerebral angiography. The resulting models leverage the computational efficiency of 3D Gaussian Splatting, achieving near-real-time rendering performance competitive with state-of-the-art reconstruction methods. The segmentation of brain vessels using nnU-Net and our trained model achieved an accuracy of 84.21%, highlighting the improvement in the performance of the proposed approach. Overall, our pipeline significantly improves both the efficiency and accuracy of volumetric cerebral vasculature reconstruction, providing a robust foundation for quantitative clinical analysis and enhanced guidance during endovascular procedures.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

20202 - Communication engineering and systems

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2026

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

AI

ISSN

—

e-ISSN

2673-2688

Volume of the periodical

7

Issue of the periodical within the volume

1

Country of publishing house

CH - SWITZERLAND

Number of pages

26

Pages from-to

1-26

UT code for WoS article

001669852500001

EID of the result in the Scopus database

—