Automatic segmentation and modeling of the aortic vessel tree: Overview of the SEG.A 2023 aorta segmentation challenge.
Authors
Jin Y,Pepe A,Melito GM,Chen Y,Ma G,Byeon Y,Kim H,Kim K,Park D,Choi E,Hwang D,Myronenko A,Yang D,He Y,Xu D,El-Ghotni A,Nabil M,El-Kady H,Ayyad A,Nasr A,Wodzinski M,Müller H,Kim H,Shin Y,Khan A,Asad M,Zolotarev A,Roney C,Mathur A,Benning M,Slabaugh G,Vagenas TP,Georgas K,Matsopoulos GK,Zhang J,Zhang Z,Huang L,Mayer C,Mächler H,Egger J
Affiliations (23)
Affiliations (23)
- Zhejiang Lab, Hangzhou, 311100, Zhejiang, China; Institute for Artificial Intelligence (AI) in Medicine (IKIM), University Medicine Essen (AöR), Girardetstr. 2, Essen, 45131, NRW, Germany; Institute of Computer Graphics and Vision (ICG), Graz University of Technology, Inffeldgasse 16/II, Graz, 8010, Styria, Austria. Electronic address: [email protected].
- Institute of Computer Graphics and Vision (ICG), Graz University of Technology, Inffeldgasse 16/II, Graz, 8010, Styria, Austria. Electronic address: [email protected].
- Institute of Mechanics (IFM), Graz University of Technology, Kopernikusgasse 24/IV, Graz, 8010, Styria, Austria.
- Zhejiang Lab, Hangzhou, 311100, Zhejiang, China; Soft Science Laboratory of Zhejiang Province, Hangzhou, Zhejiang, China.
- School of Intelligent Science and Technology, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, 310024, Zhejiang, China.
- School of Electrical and Electronic Engineering, Yonsei University, Seoul, Republic of Korea.
- School of Electrical and Electronic Engineering, Yonsei University, Seoul, Republic of Korea; Artificial Intelligence and Robotics Institute, Korea Institute of Science and Technology, Seoul, Republic of Korea.
- Department of Artificial Intelligence, Yonsei University, Seoul, Republic of Korea.
- School of Electrical and Electronic Engineering, Yonsei University, Seoul, Republic of Korea; Artificial Intelligence and Robotics Institute, Korea Institute of Science and Technology, Seoul, Republic of Korea; Department of Oral and Maxillofacial Radiology, Yonsei University College of Dentistry, Seoul, Republic of Korea; Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine, Seoul, Republic of Korea.
- NVIDIA, Santa Clara, CA, United States.
- Brightskies Inc., Alexandria, Egypt.
- Department of Measurement and Electronics, AGH University of Krakow, Krakow, Poland; Institute of Informatics, University of Applied Sciences Western Switzerland, Sierre, Switzerland.
- Institute of Informatics, University of Applied Sciences Western Switzerland, Sierre, Switzerland; Medical Faculty, University of Geneva, Geneva, Switzerland.
- School of Electrical and Electronic Engineering, Yonsei University, Seoul, Republic of Korea; Probe Medical, Seoul, Republic of Korea.
- Digital Environment Research Institute (DERI), Queen Mary University of London, UK.
- Digital Environment Research Institute (DERI), Queen Mary University of London, UK; School of Engineering and Materials Science, Queen Mary University of London, UK.
- Barts Heart Centre, Barts Health NHS Trust, UK; Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University of London, UK; NIHR Barts Biomedical Research Centre, Queen Mary University of London, UK.
- Department of Computer Science, University College London, UK.
- Biomedical Engineering Lab (BEL), School of Electrical and Computer Engineering, National Technical University of Athens, Athens, 15780, Greece.
- College of Computer and Data Science, Fuzhou University, Fuzhou, 350108, Fujian, China.
- Intelligent Image Processing and Analysis Laboratory, Fuzhou University, Fuzhou, 350108, Fujian, China.
- Division of Cardiac Surgery, Department of Surgery, Medical University of Graz, Graz, 8036, Styria, Austria.
- Institute for Artificial Intelligence (AI) in Medicine (IKIM), University Medicine Essen (AöR), Girardetstr. 2, Essen, 45131, NRW, Germany; Institute of Computer Graphics and Vision (ICG), Graz University of Technology, Inffeldgasse 16/II, Graz, 8010, Styria, Austria; Cancer Research Center Cologne Essen (CCCE), University Medicine Essen (AöR), Essen, 45147, NRW, Germany; Center for Virtual and Extended Reality in Medicine (ZvRM), University Medicine Essen (AöR), Essen, 45147, NRW, Germany; Faculty of Computer Science, University of Duisburg-Essen (UDE), Essen, 45127, NRW, Germany. Electronic address: [email protected].
Abstract
The automated analysis of the aortic vessel tree (AVT) from computed tomography angiography (CTA) is crucial for clinical applications but lacks shared, high-quality data. To address this, we launched the SEG.A. challenge, introducing a large, public, multi-institutional dataset for AVT segmentation and benchmarking automated algorithms. The challenge results showed a strong trend toward deep learning, with 3D U-Net architectures being most effective. The winning solution used an ensemble-based strategy, highlighting the value of model ensembling for robust AVT segmentation. Performance strongly correlated with algorithmic design, notably the use of customized post-processing and training data characteristics. This initiative establishes a new performance benchmark and provides a lasting resource to drive future innovation toward robust, clinically translatable AVT analysis tools.
Topics
Journal Article