ImFusion Suite

Discover our software for medical image analysis

As a standalone software, the ImFusion Suite provides high-performance visualization and processing of 2D, 3D and 4D medical data sets paired with user-friendly and versatile interactions. With a particular focus on efficient implementations on both CPU and GPU, it features a broad variety of state-of-the-art algorithms including image reconstruction, registration, segmentation and machine learning. Its plugin system allows users to extend the software with additional functionalities, but also integrate their own algorithms.

The ImFusion Suite has been designed for engineers and researchers looking for a powerful toolbox of complex algorithms, as well as clinicians interested in a more advanced analysis of their patients' images. It has not only been successfully applied in a number of academic publications both in-house and from other labs, but is also driving a growing number of medical products.

Core Features

  • Supported Data: 2D/3D/4D single or muti-channels images, as well as videos
  • Modalities: CT, CBCT, MRI, ultrasound, others/secondary storage
  • DICOM (single- and multi-frame files, graphical browser, DICOMDIR, PACS connectivity)
  • Main Formats: MetaImage (mhd, mha), NIFTI, 16-bit PNG/TIFF/JPEG, etc.
  • Tool dialog to load raw binary files with arbitrary type and dimension
  • OpenIGTLink Integration
  • 3D Surface meshes (STL, PLY, OBJ) and point clouds
  • Standard and oblique multi-planar reformatting (MPR)
  • Fast GPU shaded multi volume rendering, including DRR, MIP, iso-surface modes
  • Customizable curved planar reformatting/panorama views
  • Support for image masks and deformation fields
  • Flexible view layouts including side-by-side for fusion, larger focus view
  • Blending and fusion of arbitrary 2D and 3D/4D image data from different modalities
  • Annotations natively residing in 3D coordinates (labels, lines, angles, curves, meshes etc.)
  • Own XML-based workspaces, allowing for reproducible processing and display
  • Workspaces can be automatically executed on a batch of datasets
  • Standalone console application (without GUI) able to run workspaces
  • Interactive registration with landmarks, visual superimposition, side-by-side, transformation editor
  • Automatic image-based registration with rigid, affine and free-form deformation models
  • Efficient GPU implementation of standard similarity measures (SAD, SSD, Mutual Information, Cross-Correlation, Local Cross-Correlation)
  • Our signature multi-modal registration (CT, MRI, US) with 3D patch-based LC2 similarity
  • Fast and global distance volume based surface registration
More details...
  • Manual multi-labeling of 2D and 3D data sets
  • Thresholding methods, Connected component analysis, Fast marching
  • Graph-based semi-automatic segmentation of any anatomy in 2D or 3D, iterative refinement
  • Segmentation refinement with image matting
  • Dedicated segmentation algorithms (e.g.tubular structures, wires, surfaces)
  • Smart-spline interactive curve fitting
  • Export segmentation results as binary masks, contours, meshes with chosen smoothing
More details...
  • Deep Learning library integration for neural network training and deployment
  • Powerful Random Forest implementation with features computed on-the-fly
  • Support for 2D/3D and multi-channel images
  • Classification and regression models, both pixel-wise and image-wise
  • Toolset for easy and efficient data annotation
  • Integration with registration/segmentation algorithms, allowing powerful automated workflows
  • Interactive image features editor to assemble learning-based algorithms on arbitrary data
More details...

Specialized Plugins

  • High-quality live compounding of tracked freehand ultrasound data
  • Image-based algorithm for precise sensor-to-probe calibration and registration
  • Extended field-of-view ultrasound reconstruction from matrix-array volumes
  • Simulation of ultrasound from CT or MRI, including refraction, speckle and other physical properties
More details...
  • Fast iterative reconstruction on the GPU, including ROI/truncation handling, statistical priors
  • Tools for both geometric and radiometric cone-beam device calibration
  • Automatic detection of unexpected patient or device motion, compensation in reconstruction
More details...
  • Real-time GPU-based reconstruction of surfaces, e.g. patient torso/extremities from depth sensors
  • Mesh post-processing for 3D printing (closing holes, reducing mesh complexity, ...)
  • Multi-sensor support for instant whole-object acquisition
More details...

Demo

Try it out !

  • The demo version of the ImFusion Suite is available for free for non-commercial use on Windows and Ubuntu (a MacOS version is in preparation).

    This version lets you import all supported images and explore the full visualization capabilities of the software.

    You can run image registration and interactive segmentation on any of your data but all export functions are disabled.

Suite

Unlock all features

  • By purchasing the ImFusion Suite software, you gain access to all available algorithms in terms of image registration, segmentation and machine learning. All export functions are also unlocked.

    More specialized plugins can be purchased separately depending on your needs.

    We also provide documentation, limited support and free minor updates during one year.

SDK

Create your own application

  • The SDK version gives you access to a full C++ software development kit based on the ImFusion Suite. This means that you can either write your own plugins for the ImFusion Suite, or integrate our framework components into your application.

    This version also comes with support, helping you to leverage the full capabilities of our framework.