# Deep Medial Voxels: Learned Medial Axis Approximations for Anatomical Shape Modeling

arXiv: https://arxiv.org/abs/2403.11790 · HTML: https://mlsanity.com/paper/2403.11790/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 75 references that are in the map.
- First posted on arXiv 18 Mar 2024.

## Builds on (most cited first, 19 of 19)

- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [A large annotated medical image dataset for the development and evaluation of segmentation algorithms](https://mlsanity.com/paper/1902.09063/) (2019)
- [clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://mlsanity.com/paper/2003.07311/) (2020)
- [Real-time Scene Text Detection with Differentiable Binarization](https://mlsanity.com/paper/1911.08947/) (2019)
- [Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images](https://mlsanity.com/paper/2007.10732/) (2020)
- [Points2Surf: Learning Implicit Surfaces from Point Cloud Patches](https://mlsanity.com/paper/2007.10453/) (2020)
- [Voxel2Mesh: 3D Mesh Model Generation from Volumetric Data](https://mlsanity.com/paper/1912.03681/) (2019)
- [Deep Distance Transform for Tubular Structure Segmentation in CT Scans](https://mlsanity.com/paper/1912.03383/) (2019)
- [Point2Skeleton: Learning Skeletal Representations from Point Clouds](https://mlsanity.com/paper/2012.00230/) (2020)
- [Coverage Axis: Inner Point Selection for 3D Shape Skeletonization](https://mlsanity.com/paper/2110.00965/) (2021)
- [ImageTBAD: A 3D Computed Tomography Angiography Image Dataset for Automatic Segmentation of Type-B Aortic Dissection](https://mlsanity.com/paper/2109.00374/) (2021)
- [Deep Medial Fields](https://mlsanity.com/paper/2106.03804/) (2021)
- [Simplicial complexes: higher-order spectral dimension and dynamics](https://mlsanity.com/paper/2001.05934/) (2020)
- [SEG-MAT: 3D Shape Segmentation Using Medial Axis Transform](https://mlsanity.com/paper/2010.11488/) (2020)
- [LSMAT Least Squares Medial Axis Transform](https://mlsanity.com/paper/2010.05066/) (2020)
- [Structure-Preserving Instance Segmentation via Skeleton-Aware Distance Transform](https://mlsanity.com/paper/2310.05262/) (2023)
- [Efficient split-step schemes for fluid-structure interaction involving incompressible generalised Newtonian flows](https://mlsanity.com/paper/2108.07477/) (2021)

## Abstract (arXiv)

Shape reconstruction from imaging volumes is a recurring need in medical image analysis. Common workflows start with a segmentation step, followed by careful post-processing and,finally, ad hoc meshing algorithms. As this sequence can be timeconsuming, neural networks are trained to reconstruct shapes through template deformation. These networks deliver state-ofthe-art results without manual intervention, but, so far, they have primarily been evaluated on anatomical shapes with little topological variety between individuals. In contrast, other works favor learning implicit shape models, which have multiple benefits for meshing and visualization. Our work follows this direction by introducing deep medial voxels, a semi-implicit representation that faithfully approximates the topological skeleton from imaging volumes and eventually leads to shape reconstruction via convolution surfaces. Our reconstruction technique shows potential for both visualization and computer simulations.