Abstract #2317

Implementing compressed sensing with deep image prior to reconstruct undersampled dynamic contrast-enhanced MRI data of the breast

Kalina P Slavkova¹, Julie C DiCarlo^2,3, David M Van Veen⁴, Anum K Syed⁵, Ajil Jalal⁴, John Virostko⁶, Anna G Sorace⁷, Alexandros G Dimakis^4,8, and Thomas E Yankeelov^2,5,6,9

¹Physics, University of Texas at Austin, Austin, TX, United States, ²Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, United States, ³Livestrong Cancer Institutes, University of Texas at Austin, Austin, TX, United States, ⁴Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, United States, ⁵Biomedical Engineering, University of Texas at Austin, Austin, TX, United States, ⁶Medicine, University of Texas at Austin, Austin, TX, United States, ⁷Biomedical Engineering, University of Alabama at Birmingham, Birmingham, AL, United States, ⁸Wireless Networking and Communications Group, University of Texas at Austin, Austin, TX, United States, ⁹Oncology, University of Texas at Austin, Austin, TX, United States

We evaluate the ability of the compressed sensing with deep image prior (CS-DIP) algorithm to reconstruct undersampled dynamic contrast-enhanced MRI data of the breast. The performance of the reconstruction is evaluated by comparing quantitative parameters computed from the reconstructed data to the original parameter values computed from fully-sampled data. We hypothesize that CS-DIP will enable dramatically fewer k-space measurements, thereby allowing for higher temporal (while maintaining spatial) resolution of breast MRI scans.

This abstract and the presentation materials are available to members only; a login is required.

Join Here