Euler Characteristic Transform Based Topological Loss for Reconstructing 3D Images from Single 2D Slices

TL;DR

This paper introduces a novel topological loss function based on the Euler Characteristic Transform to improve 3D shape reconstruction from single 2D slices, especially in limited data scenarios.

Contribution

The paper proposes a new topological loss function that enhances neural network reconstructions by incorporating shape topology, demonstrated within a state-of-the-art model.

Findings

Improved 3D reconstructions with the topological loss.

Effective in limited data regimes.

The loss function is stable and injective.

Abstract

The computer vision task of reconstructing 3D images, i.e., shapes, from their single 2D image slices is extremely challenging, more so in the regime of limited data. Deep learning models typically optimize geometric loss functions, which may lead to poor reconstructions as they ignore the structural properties of the shape. To tackle this, we propose a novel topological loss function based on the Euler Characteristic Transform. This loss can be used as an inductive bias to aid the optimization of any neural network toward better reconstructions in the regime of limited data. We show the effectiveness of the proposed loss function by incorporating it into SHAPR, a state-of-the-art shape reconstruction model, and test it on two benchmark datasets, viz., Red Blood Cells and Nuclei datasets. We also show a favourable property, namely injectivity and discuss the stability of the topological loss function based on the Euler Characteristic Transform.