Abstract #0224

Robust Multi-shot EPI with Untrained Artificial Neural Networks: Unsupervised Scan-specific Deep Learning for Blip Up-Down Acquisition (BUDA)

Tae Hyung Kim^1,2,3, Zijing Zhang^1,2,4, Jaejin Cho^1,2, Borjan Gagoski^2,5, Justin Haldar³, and Berkin Bilgic^1,2

¹Athinoula A. Martinos Center for Biomedical Imaging, Boston, MA, United States, ²Radiology, Harvard Medical School, Boston, MA, United States, ³Electrical Engineering, University of Southern California, Los Angeles, CA, United States, ⁴State Key Laboratory of Modern Optical Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, China, ⁵Boston Children's Hospital, Boston, MA, United States

Blip Up-Down Acquisition (BUDA) has been successful in generating distortion-free multi-shot EPI (msEPI) without navigators, utilizing a fieldmap and structured low-rank constraints. Recently, a scan-specific artificial neural network (ANN) motivated by structured low-rank modeling, named LORAKI, has been proposed for refined MRI reconstruction, where its training employed fully-sampled autocalibrated signal (ACS). Although applying LORAKI framework to BUDA is beneficial, acquiring fully-sampled ACS for msEPI is not practical. We propose scan-specific unsupervised ANNs for improved BUDA msEPI without training data. Experiment results indicate that the proposed BUDA-LORAKI exhibits advantages, with up to 1.5x reduction in NRMSE compared to standard BUDA reconstruction.

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

Join Here