Self‐supervised learning of physics‐guided reconstruction neural networks without fully sampled reference data

By Burhaneddin Yaman, S. A. Hosseini, Steen Moeller, J. Ellermann, Kamil Ugurbil, Mehmet Akçakaya. Magnetic Resonance in Medicine, 2019

360 citations recorded by the source corpus.

To develop a strategy for training a physics‐guided MRI reconstruction neural network without a database of fully sampled data sets.

Subfields: Radiation, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/675aa0baefd11cbdd0336d69b88e845f9df65450

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Radiation

1. Richard Baraniuk
2. Christopher A. Metzler

In Radiology, Nuclear Medicine and Imaging

1. Richard Baraniuk
2. Rebecca M. Willett
3. A. Dimakis
4. Ajil Jalal

Citations in the corpus

• Deep Learning Techniques for Inverse Problems in Imaging (2020, background): “This is known as self-supervision, and has been studied in [87, 111] to learn autoencoders for estimating images x from noisy measurements y.”
• Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction (2021, neutral): “based on machine learning [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14].”