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

03/08/2023
by   Kalyan Varma Nadimpalli, et al.
45

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.

READ FULL TEXT
research
09/06/2023

Euler Characteristics and Homotopy Types of Definable Sublevel Sets

Given a continuous definable function f: S →ℝ on a definable set S, we s...
research
03/03/2022

Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D Reconstruction

Reconstructing 3D objects from 2D images is both challenging for our bra...
research
07/26/2023

The Weighted Euler Characteristic Transform for Image Shape Classification

The weighted Euler characteristic transform (WECT) is a new tool for ext...
research
08/28/2023

Statistical Inference on Grayscale Images via the Euler-Radon Transform

Tools from topological data analysis have been widely used to represent ...
research
03/23/2023

Stability and Inference of the Euler Characteristic Transform

The Euler characteristic transform (ECT) is a signature from topological...
research
07/30/2021

Topological Similarity Index and Loss Function for Blood Vessel Segmentation

Blood vessel segmentation is one of the most studied topics in computer ...
research
11/28/2018

Challenges in Reconstructing Shapes from Euler Characteristic Curves

Shape recognition and classification is a problem with a wide variety of...

Please sign up or login with your details

Forgot password? Click here to reset