Dr. Jerry L. Prince presented his work: “Medical Image Synthesis: Methods and Applications”.
According to Dr. Prince, the acquisition of truly calibrated magnetic resonance images is not currently possible. Scanners and pulse sequences are different—in subtle ways sometimes and quite dramatic ways more often. Manufacturers have different strategies for optimizing their image quality and MR techs might change a parameter to try to improve the image quality on any given day. As a consequence, the use of MR images for automatic image analysis yields inconsistent results. We have been exploring image synthesis methods to address this problem and are hopeful that through synthesis we will be able to obtain more consistent image analysis results. If successful, the use of automatic image analysis methods applied to MR images might become a more important part of clinical practice in the future. Four methods and a variety of applications and their results are presented in this talk. Sparse reconstruction is an important theme throughout, and image segmentation and registration are key methods that serve to demonstrate improvements. Although our results are promising, this new area of research is controversial and its future impact is uncertain. Dr. Prince concluded with some ideas about future directions and some thoughts about what might be possible in the future.
Dr. Jerry L. Prince
William B. Kouwenhoven Professor
Electrical and Computer Engineering
Johns Hopkins University
