Abstract
Personalised 3D vascular models are valuable for diagnosis, prognosis and treatment planning in patients with cardiovascular disease. Traditionally, such models have been constructed with explicit representations such as meshes and voxel masks, or implicit representations such as radial basis functions or atomic (cylindrical) shapes. Here, we propose to represent surfaces by the zero level set of their signed distance function (SDF) in a differentiable implicit neural representation (INR). This allows us to model complex vascular structures with a representation that is implicit, continuous, light-weight, and easy to integrate with deep learning algorithms. We here demonstrate the potential of this approach with three practical examples. First, we obtain an accurate and watertight surface for an abdominal aortic aneurysm (AAA) from CT images and show robust fitting from as few as 200 points on the surface. Second, we simultaneously fit nested vessel walls in a single INR without intersections. Third, we show how 3D models of individual arteries can be smoothly blended into a single watertight surface. Our results show that INRs are a flexible representation with potential for minimally interactive annotation and manipulation of complex vascular structures.
Original language | English |
---|---|
Pages | 79-90 |
DOIs | |
Publication status | Accepted/In press - 2022 |
Event | 13th Workshop of Statistical Atlases and Computational Modeling of the Heart, STACOM 2022 - Singapore, Singapore Duration: 18 Sept 2022 → 18 Sept 2022 |
Conference
Conference | 13th Workshop of Statistical Atlases and Computational Modeling of the Heart, STACOM 2022 |
---|---|
Abbreviated title | STACOM 2022 |
Country/Territory | Singapore |
City | Singapore |
Period | 18/09/22 → 18/09/22 |
Keywords
- Implicit neural representations
- Vascular model
- Abdominal aortic aneurysm
- Signed distance function
- Level set
Fingerprint
Dive into the research topics of 'Going Off-Grid: Continuous Implicit Neural Representations for 3D Vascular Modeling'. Together they form a unique fingerprint.Prizes
-
File