Meeting Banner
Abstract #0126

LAPNet: Deep-learning based non-rigid motion estimation in k-space from highly undersampled respiratory and cardiac resolved acquisitions

Thomas Küstner1,2, Jiazhen Pan3, Haikun Qi2, Gastao Cruz2, Kerstin Hammernik3,4, Christopher Gilliam5, Thierry Blu6, Sergios Gatidis1, Daniel Rueckert3,4, René Botnar2, and Claudia Prieto2
1Department of Radiology, Medical Image and Data Analysis (MIDAS), University Hospital of Tübingen, Tübingen, Germany, 2School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom, 3AI in Medicine and Healthcare, Klinikum rechts der Isar, Technical University of Munich, München, Germany, 4Department of Computing, Imperial College London, London, United Kingdom, 5RMIT, University of Melbourne, Melbourne, Australia, 6Chinese University of Hong Kong, Hong Kong, Hong Kong

Estimation of non-rigid motion is an important task in respiratory and cardiac motion correction. Usually, this problem is formulated in image space via diffusion, parametric-spline or optical flow methods. However, image-based registration can be impaired by aliasing artefacts or by estimating in low image resolution in cases of highly accelerated acquisitions. In this work, we propose a novel deep learning-based non-rigid motion estimation directly in k-space, named LAPNet. The proposed method, inspired by optical flow, is compared against registration in image space and tested for respiratory and cardiac motion as well as different acquisition trajectories providing a generalizable diffeomorphic registration.

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

Join Here