Welcome to FastGeodis’s documentation!

Intro

FastGeodis provides efficient CPU (OpenMP) and GPU (CUDA) implementations of Generalised Geodesic Distance Transform in PyTorch for 2D and 3D input data based on parallelisable raster scan ideas from [1]. It includes methods for computing Geodesic, Euclidean distance transform and mixture of both.

2D images: 1 of 4 passes	3D volumes: 1 of 6 passes

The above raster scan method can be parallelised for each row/plane on an available device (CPU or GPU). This leads to significant speed up as compared to existing non-parallelised raster scan implementations (e.g. https://github.com/taigw/GeodisTK). Python interface is provided (using PyTorch) for enabling its use in deep learning and image processing pipelines.

See Methodology section for more details of the implemented algorithm.

1. Criminisi, Antonio, Toby Sharp, and Khan Siddiqui. “Interactive Geodesic Segmentation of n-Dimensional Medical Images on the Graphics Processor.” Radiological Society of North America (RSNA), 2009.

Getting Started

For information on getting started with using FastGeodis, including installation, dependencies, and other similar topics, see Getting Started page.

Table of Contents

Use table of contents below, or on the left panel to explore this documentation.

• Introduction
• Methodology
  • Generalised Geodesic Distance Transform
  • Statement of Need
  • Implementation
  • Performance Improvements
• Getting Started
  • About
  • Python Version Support
  • Installation
  • Dependencies
  • Optional Development Dependencies
  • Example Usage
• Usage Examples
  • Simplest Examples
  • Available Examples