MITT: Medical Image Tracking Toolbox

Automatic license generator back online!

Please contact sandroqueiros [at] if you have any issue getting the software/license.

The Medical Image Tracking Toolbox (MITT) was designed to ease the customization of image tracking solutions in the medical field. It is built upon an object-based image tracking algorithm – the anatomical affine optical flow (AAOF). Several AAOF variants have been embedded in MITT, increasing the toolbox’s versatility and permitting its adaptation towards multiple applications. While its workflow principles make it suitable to deal with both 2D or 3D image sequences, its underlying modules, together with a command-line interface, permit an easy setup of computationally efficient tracking solutions, even for users with limited programming skills.

MITT is implemented in C/C++, with both CPU- and GPU-based executables, for Microsoft Windows ® x64 OS, being available. A MATLAB-to-C++ interface is also available, allowing to take advantage of MATLAB for code prototyping and of C/C++ for computational speed.

Further details about MITT or the underlying algorithms can be found in the publications listed below.

MITT permits the tracking of multiple type of objects, from contours, multi-contours, surfaces and multi-surfaces, with several customization features being available through a simple parameter text file.

MITT offers the possibility to easily design tracking solutions for multiple modalities.

MITT can also be used for dense motion field estimation, which allows the simultaneous tracking of multiple contours or landmarks.

List of publications:

  • MITT:
    • S. Queirós, P. Morais, D. Barbosa, J. C. Fonseca, J. L. Vilaça, and J. D’hooge, “MITT: Medical Image Tracking Toolbox,” IEEE Transactions on Medical Imaging, 2018.

  • AAOF algorithm:
    • D. Barbosa, B. Heyde, T. Dietenbeck, D. Friboulet, J. D’hooge, and O. Bernard, “Fast left ventricle tracking in 3D echocardiographic data using anatomical affine optical flow,” in Functional Imaging and Modeling of the Heart (FIMH2013), 2013, pp. 191-199.

    • S. Queirós, D. Barbosa, B. Heyde, P. Morais, J. L. Vilaça, D. Friboulet, O. Bernard, and J. D’hooge, “Fast automatic myocardial segmentation in 4D cine CMR datasets,” Medical Image Analysis, vol. 18, pp. 1115-1131, 2014.

    • S. Queirós, J. L. Vilaça, P. Morais, J. C. Fonseca, J. D’hooge, and D. Barbosa, “Fast left ventricle tracking in CMR images using localized anatomical affine optical flow,” in SPIE Medical Imaging, Orlando, USA, 2015, pp. 941306-941306-7.

    • S. Queirós, J. L. Vilaça, P. Morais, J. C. Fonseca, J. D’hooge, and D. Barbosa, “Fast left ventricle tracking using localized anatomical affine optical flow,” International Journal for Numerical Methods in Biomedical Engineering, vol. 33, p. e2871, 2017.

    • J. Pedrosa, S. Queirós, O. Bernard, J. Engvall, T. Edvardsen, E. Nagel, et al., “Fast and Fully Automatic Left Ventricular Segmentation and Tracking in Echocardiography Using Shape-Based B-Spline Explicit Active Surfaces,” IEEE Transactions on Medical Imaging, vol. 36, pp. 2287-2296, 2017.

This work was funded by: