Events Calendar

Low Rank, Sparsity and Beyond: Novel Adaptive Reconstruction Algorithms for Highly Accelerated Dynamic MRI

Speaker: Sajan Lingala,Ph.D., University of Iowa

Talk Title: Low Rank, Sparsity and Beyond: Novel Adaptive Reconstruction Algorithms for Highly Accelerated Dynamic MRI

Series: Medical Imaging Seminar Series

Abstract: The imaging of dynamically evolving phenomena is central to several magnetic resonance imaging (MRI) applications. The simultaneous acquisition of high spatio-temporal resolutions, extended volume coverage, good signal to noise is often challenging in dynamic MRI due to the MR hardware limitations and the risk of peripheral nerve stimulation. The main focus of this talk is to introduce novel blind or adaptive signal models to enable reconstruction from highly undersampled measurements. I will start by describing conventional compressed sensing models that utilizes “fixed bases”; discuss its challenges, and motivate why using "adaptive bases" would be beneficial. I shall then describe our contributions on adaptive models that include low rank and sparsity based modeling, blind compressed sensing, and motion compensated compressed sensing. I shall also show representative dynamic MRI applications including free breathing cardiac perfusion MRI, and parametric mapping that benefit from the acceleration provided by the proposed techniques.

Biography: Sajan Lingala completed his Masters in Biomedical Engineering at the Indian Institute of Technology Bombay (India). He is currently working towards his Phd at the University of Iowa with his thesis focused on developing novel image reconstruction algorithms for accelerated MR imaging. He is a recipient of American Heart Association predoctoral fellowship award, and a best graduate student award at the Iowa institute of Biomedical Imaging.




Host: Prof. Yoon Chul Kim

Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248

Audiences: Everyone Is Invited

Contact: Talyia Veal