Rethinking Intracranial Aneurysm Vessel Segmentation: A Perspective from Computational Fluid Dynamics Applications

TL;DR

This work introduces the IAVS dataset, a large multi-center collection of 641 3D MRA images with CFD-ready IA and IA-Vessel annotations, plus a standardized CFD applicability evaluation system and two-stage benchmarks for aneurysm localization and topology-aware IA-Vessel segmentation. A two-stage framework combining global aneurysm localization with topology-preserving segmentation markedly improves CFD readiness over end-to-end approaches, and a novel CFD applicability score enables end-to-end evaluation of segmentation outputs for downstream simulations. The results establish a practical pipeline that bridges image segmentation and hemodynamic modeling, with significant implications for CFD-informed clinical decision-making and future physics-informed methods. limitations include independent-stage training and demographic diversity concerns, suggesting avenues for end-to-end, multi-task, or physics-informed enhancements and broader, diverse validation.

Abstract

The precise segmentation of intracranial aneurysms and their parent vessels (IA-Vessel) is a critical step for hemodynamic analyses, which mainly depends on computational fluid dynamics (CFD). However, current segmentation methods predominantly focus on image-based evaluation metrics, often neglecting their practical effectiveness in subsequent CFD applications. To address this deficiency, we present the Intracranial Aneurysm Vessel Segmentation (IAVS) dataset, the first comprehensive, multi-center collection comprising 641 3D MRA images with 587 annotations of aneurysms and IA-Vessels. In addition to image-mask pairs, IAVS dataset includes detailed hemodynamic analysis outcomes, addressing the limitations of existing datasets that neglect topological integrity and CFD applicability. To facilitate the development and evaluation of clinically relevant techniques, we construct two evaluation benchmarks including global localization of aneurysms (Stage I) and fine-grained segmentation of IA-Vessel (Stage II) and develop a simple and effective two-stage framework, which can be used as a out-of-the-box method and strong baseline. For comprehensive evaluation of applicability of segmentation results, we establish a standardized CFD applicability evaluation system that enables the automated and consistent conversion of segmentation masks into CFD models, offering an applicability-focused assessment of segmentation outcomes. The dataset, code, and model will be public available at https://github.com/AbsoluteResonance/IAVS.

Figures (5)

• Figure 1: (a) Whole intracranial vasculature and local parent vessels. (b) IA-Vessel ground truth. (c) Despite the Dice score is relatively low (0.7648), no topological errors are present. (d) Although the Dice similarity coefficient is high (0.9869), topological errors are present which is unusable for CFD.
• Figure 2: An overview of the IAVS dataset and the annotation workflow. Each case encompasses seven types of standardized data: (1) whole-brain MRA images, (2) IA mask, (3) IA-Vessel mask, (4) STL models with cut inlets/outlets, (5) vascular centerlines, (6) mesh files with boundary annotations, (7) CFD analysis results.
• Figure 3: Overview of our conversion pipeline from segmentation masks to CFD models, which realizes the entire chain process from medical imaging to flow field simulation. The pipeline consists of following steps, including vascular topology inspection, morphological preprocessing, geometric model conversion, centerline generation, end face cutting, mesh enhancement, surface fitting, boundary labeling, mesh generation, and CFD computation.
• Figure 4: Our proposed two-stage framework for IA-Vessel segmentation. Stage I utilizes a detection network for global localization of aneurysms. After cropping out candidate patches, Stage II utilizes a topological-aware segmentation network for IA-Vessel segmentation to reduce topology errors.
• Figure 5: Visualization of IA-Vessel segmentation results of different methods.