Related Experiment Video
Updated: Jul 9, 2026
Three-Dimensional Printing of a Complex Aortic Anomaly
Published on: November 1, 2018
Multi-class segmentation of aortic branches and zones in computed tomography angiography: The AortaSeg24 challenge
Muhammad Imran1, Jonathan R Krebs2, Vishal Balaji Sivaraman3
1School of Data Science and Analytics, Kennesaw State University, Marietta, GA, 30060, United States; Department of Medicine, University of Florida, Gainesville, FL, 32611, United States.
Insights
A new dataset and challenge enable multi-class segmentation of the aorta in computed tomography angiography (CTA) scans, advancing diagnosis and treatment planning for aortic dissections.
Area of Science:
- Medical Imaging
- Computer Vision
- Cardiovascular Research
Background:
- Multi-class segmentation of the aorta in computed tomography angiography (CTA) is crucial for diagnosing aortic dissections and planning endovascular treatments.
- Current methods often simplify aortic segmentation to a binary problem, hindering detailed measurements of branches and zones.
- A lack of open-source datasets impedes the development of advanced multi-class aortic segmentation techniques.
Purpose of the Study:
- Introduce the first comprehensive dataset for multi-class aortic segmentation using CTA scans.
- Facilitate the development and validation of novel algorithms for detailed aortic analysis.
- Organize the AortaSeg24 MICCAI Challenge to drive innovation in aortic segmentation.
Main Methods:
- Creation of a novel dataset with 100 CTA volumes annotated for 23 aortic branches and zones.
- Organization of the AortaSeg24 MICCAI Challenge, attracting 121 international teams.
- Evaluation of submitted algorithms using Dice Similarity Coefficient (DSC) and Normalized Surface Distance (NSD).
Main Results:
- The AortaSeg24 challenge fostered the development of advanced segmentation methods, including cascaded models and custom loss functions.
- Top-performing teams utilized state-of-the-art frameworks like nnU-Net, demonstrating significant progress in multi-class aortic segmentation.
- Analysis identified key approaches and techniques employed by leading algorithms in accurately segmenting complex aortic structures.
Conclusions:
- The AortaSeg24 challenge and dataset provide a vital resource for advancing multi-class aortic segmentation in CTA.
- Publicly available data, code, and top-performing methods will accelerate research in aortic dissection diagnosis and treatment.
- This initiative supports the development of more precise and clinically applicable AI tools for cardiovascular imaging.
Abstract:
Multi-class segmentation of the aorta in computed tomography angiography (CTA) scans is essential for diagnosing and planning complex endovascular treatments for patients with aortic dissections. However, existing methods reduce aortic segmentation to a binary problem, limiting their ability to measure diameters across different branches and zones. Furthermore, no open-source dataset is currently available to support the development of multi-class aortic segmentation methods. To address this gap, we organized the AortaSeg24 MICCAI Challenge, introducing the first dataset of 100 CTA volumes annotated for 23 clinically relevant aortic branches and zones. This dataset was designed to facilitate both model development and validation. The challenge attracted 121 teams worldwide, with participants leveraging state-of-the-art frameworks such as nnU-Net and exploring novel techniques, including cascaded models, data augmentation strategies, and custom loss functions. We evaluated the submitted algorithms using the Dice Similarity Coefficient (DSC) and Normalized Surface Distance (NSD), highlighting the approaches adopted by the top five performing teams. This paper presents the challenge design, dataset details, evaluation metrics, and an in-depth analysis of the top-performing algorithms. The annotated dataset, evaluation code, and implementations of the leading methods are publicly available to support further research. All resources can be accessed at https://aortaseg24.grand-challenge.org.
