Towards the Automatic Segmentation, Modeling and Meshing of the Aortic Vessel Tree from Multicenter Acquisitions: An Overview of the SEG.A. 2023 Segmentation of the Aorta Challenge

TL;DR

This paper introduces the SEG.A. 2023 challenge, providing a large multi-institutional dataset for automated aortic vessel tree segmentation from CTA, benchmarking deep learning methods, and highlighting ensemble approaches and data characteristics for improved performance.

Contribution

It presents a new publicly available dataset and benchmark for AVT segmentation, emphasizing deep learning dominance and ensemble benefits, to advance clinical translation.

Findings

Deep learning, especially 3D U-Net, dominates top methods.

Ensemble models outperform individual algorithms.

Performance depends on data quality and post-processing techniques.

Abstract

The automated analysis of the aortic vessel tree (AVT) from computed tomography angiography (CTA) holds immense clinical potential, but its development has been impeded by a lack of shared, high-quality data. We launched the SEG.A. challenge to catalyze progress in this field by introducing a large, publicly available, multi-institutional dataset for AVT segmentation. The challenge benchmarked automated algorithms on a hidden test set, with subsequent optional tasks in surface meshing for computational simulations. Our findings reveal a clear convergence on deep learning methodologies, with 3D U-Net architectures dominating the top submissions. A key result was that an ensemble of the highest-ranking algorithms significantly outperformed individual models, highlighting the benefits of model fusion. Performance was strongly linked to algorithmic design, particularly the use of customized post-processing steps, and the characteristics of the training data. This initiative not only establishes a new performance benchmark but also provides a lasting resource to drive future innovation toward robust, clinically translatable tools.