Parametric shape models for vessels learned from segmentations via differentiable voxelization
This work addresses the challenge of integrating multiple vessel representations for medical applications, offering a novel approach that could enhance analysis and manipulation in domains like vascular imaging, though it appears incremental in combining existing techniques.
The authors tackled the problem of disjoint representations of vessels in medical imaging by proposing a framework that integrates voxelization, meshes, and parametric models through differentiable transformations, enabling automatic extraction of parametric shape models from segmentations without ground-truth shape parameters, with results demonstrating accurate geometry capture in complex vessels like aortas and aneurysms.
Vessels are complex structures in the body that have been studied extensively in multiple representations. While voxelization is the most common of them, meshes and parametric models are critical in various applications due to their desirable properties. However, these representations are typically extracted through segmentations and used disjointly from each other. We propose a framework that joins the three representations under differentiable transformations. By leveraging differentiable voxelization, we automatically extract a parametric shape model of the vessels through shape-to-segmentation fitting, where we learn shape parameters from segmentations without the explicit need for ground-truth shape parameters. The vessel is parametrized as centerlines and radii using cubic B-splines, ensuring smoothness and continuity by construction. Meshes are differentiably extracted from the learned shape parameters, resulting in high-fidelity meshes that can be manipulated post-fit. Our method can accurately capture the geometry of complex vessels, as demonstrated by the volumetric fits in experiments on aortas, aneurysms, and brain vessels.