Git Product home page Git Product logo

cldice's Introduction

README

clDice - a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation

CVPR 2021

Authors: Suprosanna Shit and Johannes C. Paetzold et al.

@article{shit2020cldice,
  title={clDice - a Topology-Preserving Loss Function for Tubular Structure Segmentation},
  author={Shit, Suprosanna and Paetzold, Johannes C and Sekuboyina, Anjany and Zhylka, Andrey and Ezhov, Ivan and Unger, Alexander and Pluim, Josien PW and Tetteh, Giles and Menze, Bjoern H},
  journal={arXiv preprint arXiv:2003.07311},
  year={2020}
}

Abstract

Accurate segmentation of tubular, network-like structures, such as vessels, neurons, or roads, is relevant to many fields of research. For such structures, the topology is their most important characteristic; particularly preserving connectedness: in the case of vascular networks, missing a connected vessel entirely alters the blood-flow dynamics. We introduce a novel similarity measure termed centerlineDice (short clDice), which is calculated on the intersection of the segmentation masks and their (morphological) skeleta. We theoretically prove that clDice guarantees topology preservation up to homotopy equivalence for binary 2D and 3D segmentation. Extending this, we propose a computationally efficient, differentiable loss function (soft-clDice) for training arbitrary neural segmentation networks. We benchmark the soft-clDice loss on five public datasets, including vessels, roads and neurons (2D and 3D). Training on soft-clDice leads to segmentation with more accurate connectivity information, higher graph similarity, and better volumetric scores.

Table of contents

clDice Metric

In our publication we show how clDice can be used as a Metric to benchmark segmentation performance for tubular structures. The metric clDice is calculated using a "hard" skeleton using skeletonize from the scikit-image library. Other potentially more sophisticated skeletonization techniques could be integrated in to the clDice metric as well. You can find a python implementation in this repository.

clDice as a Loss function

To train neural networks with clDice we implemented a loss function. For stability reasons and to ensure a good volumetric segmentation we combine clDice with a regular Dice or binary cross entropy loss function. Moreover, we need to introduce a Soft Skeleton to make the skeletonization fully differentiable. In this repository you can find the following implementations:

  1. pytorch 2D and 3D
  2. tensorflow/Keras 2D and 3D

Soft Skeleton

To use clDice as a loss function we introduce a differentiable soft-skeletonization where an iterative min- and max-pooling is applied as a proxy for morphological erosion and dilation.

drawing

cldice's People

Contributors

jocpae avatar suprosanna avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.