In this project, we are seeking to provide a tool which presents and facilitates the visualization of fused imagery to medical specialists. This pipelined system contains three processing stages that make possible multi-modality image fusion, learning-based segmentation and identification, and exploration of these results in two or three dimensions.  The fusion stage supports the combination of multi-modal medical images into a single color image while preserving information present in the original single-modality images. The learning stage allows experts to train the system in the segmentation and recognition of task-relevant features. This learning system creates pattern recognition agents capable of segmenting or pre-screening input images. The explorer stage facilitates intuitive navigation of the fused and computer-segmented imagery.

If you would like to learn more about each of the stages click on the appropriate link

• Fusion stage

• Learning stage

• Explorer stage

 Below is a screen capture of the interface.

Several videos featuring the software have been provided for download. Please follow any of the links below.  Each of the following videos require the TSCC Codec:

• Med-LIFE Image Fusion Stage [avi, 4 MB]

• Med-LIFE Exploration Stage [avi, 18 MB]

• Med-LIFE Learning Stage's Contextual Zoom Controls [avi, 11 MB]

• Med-LIFE Learning Stage's Contextual Zoom Markings [avi, 53 MB]

Previous Videos:

• Video presenting an overview of a previous interface prototype [avi, 33 MB] [realmedia, 460 bytes].

• Video that compares the results of fusion of PD versus SPECT modalities against pure SPECT. In this video, the fusion results are displayed while the pure SPECT fades into and out of view [avi, 40 MB] [realmedia, 460 bytes].

In the news:

Relevant Publications

Aguilar, M., New, J.R., and Hasanbelliu, E. (2003). "Advances in the use of neurophysiologically-based fusion for visualization and pattern recognition of medical imagery." In Proceedings of the 6th International Conf. on Information Fusion, Cairns, Australia. [PDF]

New, J.R., Hasanbelliu, E., and Aguilar, M. (2003). "Facilitating User Interaction with Complex Systems via Hand Gesture Recognition." In Proceedings of the 2003 Southeastern ACM Conference, Savannah, GA. [PDF]

Aguilar, M. and New, J.R. (2002). "Fusion of Multi-Modality Volumetric Medical Imagery."  To appear in Proceedings of the Fifth International Conference on Information Fusion, Annapolis, MD. [PDF]

New, J. and Hasanbelliu, E.  "Med-LIFE: A System for Medical Image Visualization."  In Proc. of the 2002 College Research Symposium, Jacksonville State University, 2002. (M. Aguilar, Faculty Mentor).

Aguilar, M. and Garrett, A. “Visualization of Fused fMRI and SPECT Imagery.”  Proceedings International Conference on Mathematics and Engineering Techniques in Medicine and Biological Sciences 2001. [PDF]

M. Aguilar and A.L. Garrett, "Biologically-based sensor fusion for medical imaging", To appear in Proc. of SPIE Conference on Sensor Fusion: Architectures, Algorithms, and Applications V, 4385, 2001. [PDF]

Related Projects

Visualization of multi-spectral fusion for precision farming

Acknowledgements

This work was supported by a Faculty Research Grant awarded to the director of the laboratory by the faculty research committee and Jacksonville State University.  Opinions, interpretations, and conclusions are those of the authors and not necessarily endorsed by the committee or Jacksonville State University.