Two Gordon Center students and a post-doctoral fellow have been recognized for their excellent work on recent conference abstracts.
Yanis Djebra was granted Magna cum laude, an award given for the top 15% abstracts submitted in major categories, for his ISMRM abstract on “Manifold learning via tangent space alignment for accelerated dynamic MR imaging with highly undersampled (k,t) data”
Abstract: Many unsupervised learning methods have been proposed to discover the structure of manifolds embedded in high-dimensional input spaces. However, image reconstruction requires mapping the learned low-dimension data in the feature space back to the input space, which can be challenging if the mapping function is implicit. This work presents an image reconstruction scheme closely related to machine learning methods learning manifolds via tangent space alignment. Here, the mapping transform is explicit and learned from the data. This model is a nonlinear generalization of the Low-Rank matrix/tensor model, reconstructing undersampled MR data with lower rank than the standard Low-Rank reconstruction.
Yanis Chemli was selected for the Young Investigator awards section in the Physics, Instrumentation and Data Science council for his SNMMI Annual Meeting abstract. He will be presenting on how to go beyond the intrinsic scanner’s resolution using super resolution techniques with a real time optical motion tracker. See image for a preview of his results.
Felicitas Detmer was selected for the Young Investigator awards section in the Cardiovascular council for her SNMMI Annual Meeting abstract. She will be presenting on Imaging of mitochondrial function in doxorubicin-induced cardiotoxicity. She will talk about her study where they have shown in-vivo in seven pigs that an acute cardiotoxic effect of doxorubicin can be detected with 18F-TPP PET imaging.