Topology-Aware Segmentation Using Discrete Morse Theory

03/18/2021
by   Xiaoling Hu, et al.
10

In the segmentation of fine-scale structures from natural and biomedical images, per-pixel accuracy is not the only metric of concern. Topological correctness, such as vessel connectivity and membrane closure, is crucial for downstream analysis tasks. In this paper, we propose a new approach to train deep image segmentation networks for better topological accuracy. In particular, leveraging the power of discrete Morse theory (DMT), we identify global structures, including 1D skeletons and 2D patches, which are important for topological accuracy. Trained with a novel loss based on these global structures, the network performance is significantly improved especially near topologically challenging locations (such as weak spots of connections and membranes). On diverse datasets, our method achieves superior performance on both the DICE score and topological metrics.

READ FULL TEXT

page 2

page 3

page 5

page 8

page 9

page 14

page 15

research
12/15/2021

Structure-Aware Image Segmentation with Homotopy Warping

Besides per-pixel accuracy, topological correctness is also crucial for ...
research
06/03/2022

Learning Probabilistic Structural Representation for Biomedical Image Segmentation

Accurate segmentation of various fine-scale structures from biomedical i...
research
05/12/2022

Image Segmentation with Topological Priors

Solving segmentation tasks with topological priors proved to make fewer ...
research
07/14/2022

Enforcing connectivity of 3D linear structures using their 2D projections

Many biological and medical tasks require the delineation of 3D curvilin...
research
06/02/2023

The optimal connection model for blood vessels segmentation and the MEA-Net

Vascular diseases have long been regarded as a significant health concer...
research
05/20/2021

Semi-supervised, Topology-Aware Segmentation of Tubular Structures from Live Imaging 3D Microscopy

Motivated by a challenging tubular network segmentation task, this paper...
research
07/23/2022

BuyTheDips: PathLoss for improved topology-preserving deep learning-based image segmentation

Capturing the global topology of an image is essential for proposing an ...

Please sign up or login with your details

Forgot password? Click here to reset