FAST – Framework for heterogeneous medical image computing and visualization

fast_logo_large

FAST is an open-source cross-platform framework with the main goal of making it easier to do high-performance processing and visualization of medical images on heterogeneous systems utilizing both multi-core CPUs and GPUs. To achieve this, FAST use modern C++, OpenCL and OpenGL.

Surface mesh extracted from a large abdominal CT scan. Alpha blending ray casting rendering of a thorax CT image.

Get started

First, make sure you have the requirements installed.
Stable binary releases/installers can be downloaded for Windows and Ubuntu Linux.

To start using the framework, see the Getting started with FAST guide and examples.

FAST is also available for Python 3 through pip: pip install pyfast
Python examples can be found here.

Need help? Use the gitter chat

Main features

  • Data streaming – Processing pipelines in FAST can handle both static and dynamic/temporal data without any change to the code. FAST can stream data from movie files, your webcamera, an Intel RealSense camera, a sequence of images and even directly from ultrasound scanners such as Clarius.
  • Deep learning – FAST provides a common interface for neural networks supporting different model formats (ONNX, protobuf, SavedModel, OpenVINO, UFF) and backends (Google TensorFlow, NVIDIA TensorRT, Intel OpenVINO), making it possible to create real-time neural network pipelines.
  • High-level data management – Data objects in FAST represent data, such as an image, on all processors. FAST keeps data coherent across the different storage areas thereby removing the burden of explicit memory handling from the developer.
  • Wide data format support – FAST supports several data formats (DICOM, metaimage (MHD), regular jpg/png/bmp images, videos, HDF5, VTK polydata, whole slide images, ultrasound file format) and data types (images 2D and 3D, grayscale and color, image pyramids, surface mesh, vertices, lines, text ++).
  • High performance algorithms – FAST has several high performance parallel OpenCL implementations of common algorithms, such as marching cubes surface extraction, Gaussian smoothing, non-local means, block matching tracking and seeded region growing.
  • Fast concurrent visualization – Rendering and computation are done in separate threads to ensure smooth responsive visualizations. Several types of visualizations are supported both 3D (mesh, point, line, image slice and volume rendering) and 2D (2D image, image slice and segmentation/label rendering, whole slide image (WSI) pyramids).
  • Interoperability – FAST can be used with Python and can also be easily integrated into existing Qt applications.

Research

FAST has been described in the following research articles. If you use this framework for research please cite them:

FAST: framework for heterogeneous medical image computing and visualization
Erik Smistad, Mohammadmehdi Bozorgi, Frank Lindseth
International Journal of Computer Assisted Radiology and Surgery 2015

High Performance Neural Network Inference, Streaming, and Visualization of Medical Images Using FAST
Erik Smistad, Andreas Østvik, André Pedersen
IEEE Access 2019

Build

To setup and build the framework, see the instructions for your operating system:

  • Linux Ubuntu
  • Windows
  • Mac OS X Note: Mac OS X version is unstable and not actively maintained anymore due to Apple’s decision to stop supporting OpenCL and OpenGL.

Ultrasound image segmentation using neural netwoks. Whole slide microscopy image.

1 Response

  1. January 17, 2017

    […] Video: Real-time medical GPU-based marching cubes surface extraction with FAST […]