Aneumo: A Large-Scale Comprehensive Synthetic Dataset for Aneurysm Hemodynamics

Basic Information

• This repository hosts the Aneumo dataset, a large-scale and comprehensive synthetic dataset specifically designed for the study of aneurysm hemodynamics.

• The Aneumo dataset comprises 10,000+ 3D models (real and synthetic), categorized as follows:

  • 466 real aneurysm models, sourced from the AneuX dataset.
  • 466 aneurysm-free models, representing normal vascular structures.
  • 9,534 deformed aneurysm models, encompassing diverse aneurysm shapes, sizes, and locations.

• These synthetic models were generated through resection and deformation operations, based on 466 real aneurysm cases.

• The dataset further includes:

  • 10,000+ Medical image-like segmentation mask files, enabling the development and testing of segmentation algorithms.
  • 80,000+ Hemodynamic data obtained at eight steady-state flow rates (0.001 to 0.004 kg/s), covering critical parameters such as velocity, pressure, and wall shear stress.

• The dataset will be made available for download soon. Stay tuned for updates. Please refer to the paper for more details.

Visual Overview

Below are key visualizations illustrating the dataset generation process and sample outputs:

Figure 1: Workflow of the Aneumo dataset generation process

Figure 2: Visualization of hemodynamic parameters: Maximum velocity (left) and normalized pressure difference (right)

Acknowledgments

The development of the Aneumo dataset was made possible through the use of real-world aneurysm data, with partial contributions from the AneuX dataset.