Professor Jong-chul Ye of the Department of Bio and Brain Engineering and Hong Jeong, a doctorate student, won the first prize at the Recon Challenge held as part of a workshop sponsored by the International Society for Magnetic Resonance in Medicine (ISMRM) held in Sedona, the United States.
The workshop took place under the theme of “data sampling and image reconstruction” on Jan. 25-28 in Sedona, Arizona, the United States. The KAIST team beat out major magnetic resonance imaging groups from the U.S. and Europe.
The Recon Challenge is a biennial competition highlighting different reconstruction strategies and metrics to compare them. ISMRM is an international, nonprofit, scientific association which promotes communication, research, development, and applications in the field of magnetic resonance in medicine and biology and other related topics.
At the competition, the KAIST team presented a new dynamic MRI algorithm called k-t FOCUSS that is optimal from a compressed sensing perspective. The main contribution of the method is extension of k-t FOCUSS to a more general framework with prediction and residual encoding. The prediction provides an initial estimate while the residual encoding takes care of the remaining residual signals.