# Probabilistic Atlases to Enforce Topological Constraints

arXiv: https://arxiv.org/abs/1909.08330 · HTML: https://mlsanity.com/paper/1909.08330/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2019.

## Built on by (most cited first, 2 of 2)

- [TEDS-Net: Enforcing Diffeomorphisms in Spatial Transformers to Guarantee Topology Preservation in Segmentations](https://mlsanity.com/paper/2107.13542/) (2021)
- [Weakly Supervised Volumetric Image Segmentation with Deformed Templates](https://mlsanity.com/paper/2106.03987/) (2021)

## Abstract (arXiv)

Probabilistic atlases (PAs) have long been used in standard segmentation approaches and, more recently, in conjunction with Convolutional Neural Networks (CNNs). However, their use has been restricted to relatively standardized structures such as the brain or heart which have limited or predictable range of deformations. Here we propose an encoding-decoding CNN architecture that can exploit rough atlases that encode only the topology of the target structures that can appear in any pose and have arbitrarily complex shapes to improve the segmentation results. It relies on the output of the encoder to compute both the pose parameters used to deform the atlas and the segmentation mask itself, which makes it effective and end-to-end trainable.