Hi everyone,

You are all cordially invited to the AMLab Seminar on **Thursday 5 ^{th} November at 4:00 p.m CET** on

**Zoom**, where

**Tim Bakker**will give a talk titled ”

**Experimental design for MRI by greedy policy search**“.

**Title: **Experimental design for MRI by greedy policy search

**Abstract:** In today’s clinical practice, magnetic resonance imaging (MRI) is routinely accelerated through subsampling of the associated Fourier domain. Currently, the construction of these subsampling strategies – known as experimental design – relies primarily on heuristics. We propose to learn experimental design strategies for accelerated MRI with policy gradient methods. Unexpectedly, our experiments show that a simple greedy approximation of the objective leads to solutions nearly on-par with the more general non-greedy approach. We offer a partial explanation for this phenomenon rooted in greater variance in the non-greedy objective’s gradient estimates, and experimentally verify that this variance hampers non-greedy models in adapting their policies to individual MR images. We empirically show that this adaptivity is key to improving subsampling designs.

**Paper Link: **https://arxiv.org/pdf/2010.16262.pdf

To gain more deep insights into MRI research using Reinforcement Learning, feel free to join and discuss it! See you there 🙂 !