Multi-Class Segmentation of Aortic Branches and Zones in Computed Tomography Angiography
Clinical Relevance
The aorta is the largest artery of the body, carrying oxygenated blood from the heart to the head, neck, upper extremities, abdomen, pelvis, and lower extremities. Pathologies of the aorta and its main branches, like dissection, aneurysm, and atherosclerotic disease, can be immediate threats to life or limb, requiring prompt surgical evaluation and treatment. Advances in medical imaging and therapies, including computed tomography angiography (CTA) and the endovascular aortic stent grafts, have led to a paradigm shift in the management of aortic disease. Endovascular abdominal aortic aneurysm repair, for example, is now performed as first-line therapy in over 80% of patients. For minimally invasive repairs involving branch vessels, a detailed 3D analysis of the aortic and branch vessel anatomy is essential. This includes measuring the volume and diameter of the aorta and individual aortic branches and zones for appropriate device selection, which can be achieved by multi-class segmentation of the aorta on CTA.
AortaSeg24 Challenge
While machine learning has revolutionized 3D medical image analysis, its potential in acute uncomplicated type B aortic dissection (auTBAD), the most common aortic emergency, remains largely unexplored. In the clinical setting, auTBAD is categorized using SVS/STS zones, a detailed classification system defined by specific zones of the aorta in relation to aortic branches. Current methods for aortic segmentation often treat this as a binary segmentation problem, neglecting the essential differentiation between individual aortic branches and their relationships to SVS/STS zones.
This challenge has been proposed to address these limitations by offering the first large-scale dataset of 100 CTA volumes, which are paired with detailed annotations for the aorta, its branches, and the clinically relevant SVS/STS zones. Participating teams will have the opportunity to develop innovative algorithms for accurate, automated, and multi-class segmentation of this intricate vascular structure.
By fostering advancements in image analysis techniques for CTA, this challenge aims to:
- Improve clinical care for patients with aortic diseases by enabling accurate diagnosis, more precise surgical planning, and potentially safer, minimally invasive intervention strategies.
- Bring greater attention and research focus to auTBAD, a relatively rare and challenging disease, potentially leading to novel treatment strategies.
- Bridge interdisciplinary communication between researchers in medical image analysis, computer vision, and machine learning, paving the way for collaborative solutions to overcome technical barriers in complex aortic segmentation tasks.
Segmentations correspond with the image from top to bottom