RealTITracker A toolbox for real-time 2D/3D optical flow based
medical image registration

Welcome to RealTITracker

RealTITracker (Real-Time Image-based Tracker) is a free software written in C++, optimised for multi-CPU architecture and available on Linux and Windows platforms. The software consists of a collection of fast optical flow algorithms that are commonly used to solve real-time 2D/3D image registration problems.

A Matlab interface is provided in RealTITracker to quickly configure, test, and integrate optical-flow registration methods in a specific application.

The author underlines that RealTITracker has been developped for academic purpose only. The authors disclaim any responsability for any potential damage caused by the RealTITracker toolbox.

Update of RealTITracker

Feature of RealTITracker

Compared to other image registration techniques, the benefit of optical flow approaches is focused around the low computation time required and the minimal number of required control parameters. Optical flow algorithms thus demonstrated a great potential for medical interventional applications such as:

The reader is referred to the reviews available here, here and here for a description of state-of-the-art real-time image-guided interventions on mobile organs. For both of these applications, the optical flow algorithm requires fixating only a single parameter, which reflects the elasticity of the tracked organs. Although this parameter may theoretically be adapted for each specific data-set, a fixed value can generally be found in practice for a specific medical application.

Proof of concept of the motion estimation process performed on-line in the abdomen of a healthy volunteer for a) liver (inside green contour) and kidney (inside red contour) and b) in the pancreas (inside red contour). 2D dynamic MRI with a frame rate of respectively 10 and 3 images/s was performed under free-breathing conditions: The organ movement and deformation, estimated on the fly from MR anatomical images, was obtained on a voxel-by-voxel basis with an overall latency lower than 100 milliseconds.

Add-ons for RealTITracker

Several add-ons for RealTITracker can be downloaded from the Add-ons page.

Authors

The authors of RealTITracker are Baudouin Denis de Senneville, Luc Laffite, Cornel Zachiu and Mario Ries. Their contact information:

This software was initially developed at the MR-HIFU group, under supervision of:

on funding granted by the European Research Council (ERC). Since October 2009, Baudouin Denis de Senneville is employed with the National Center of the Scientific Research (CNRS) in France. Since September 2011, Mario Ries is employed with the MR-HIFU group at the University Medical Center Utrecht.

How to cite RealTITracker

If you use this software anywhere we would appreciate if you cite the following articles:

  • Zachiu C., Denis de Senneville B., Moonen C. T. W., Ries M., "A framework for the correction of slow physiological drifts during MR-guided HIFU therapies: Proof of concept", Medical Physics, 2015;42(7):4137-4148.

  • Zachiu C., Papadakis N., Ries M., Moonen C. T. W., Denis de Senneville B., "An improved optical flow tracking technique for real-time MR-guided beam therapies in moving organs", Physics in Medicine and Biology, 2015; In press.

    • How to use this documentation