Learning a Sampling Pattern for MRI Ferdia Sherry Supervised by Carola-Bibiane Sch¨ onlieb and Matthias J. Ehrhardt May 25, 2017 Ferdia Sherry Learning a sampling pattern for MRI May 25, 2017 1 / 6
Magnetic Resonance Imaging (a) An MRI machine in (b) An image of a knee acquired operation by MRI We model the measurements y taken by the MRI machine as y = S F u + ε and reconstruct the image from measurements y by minimising a TV-regularised least squares functional: u ∗ = argmin E TV ( u ′ , y , S , α ) . u ′ � 0 Ferdia Sherry Learning a sampling pattern for MRI May 25, 2017 2 / 6
The effect of the sampling pattern Ferdia Sherry Learning a sampling pattern for MRI May 25, 2017 3 / 6
Learning a sampling pattern Given a training set of ground truth images { u 1 , . . . , u n } and corresponding measurements { y 1 , . . . , y n } we want to determine a suitable sampling pattern S for similar images. To do this we study the bilevel problem n 1 � ℓ ( u ∗ min i , u i ) + penalty( S , α ) n S ,α i =1 where u ∗ i = argmin E TV ( u , y i , S , α ) u � 0 with ℓ a loss function measuring the reconstruction error. Ferdia Sherry Learning a sampling pattern for MRI May 25, 2017 4 / 6
A learned sampling pattern and reconstruction Ferdia Sherry Learning a sampling pattern for MRI May 25, 2017 5 / 6
Thank you for listening! Ferdia Sherry Learning a sampling pattern for MRI May 25, 2017 6 / 6
Recommend
More recommend