Learning a Generative Motion Model from Image Sequences based on a Latent Motion Matrix
This work addresses motion analysis and simulation for medical imaging, particularly in cardiac applications, offering incremental improvements in registration and interpolation tasks.
The paper tackles the problem of learning a generative motion model from image sequences for spatio-temporal registration, achieving improved registration accuracy and smoother deformations compared to three state-of-the-art algorithms in cardiac cine-MRI, and demonstrating better motion reconstruction from sequences with missing frames than linear and cubic interpolation.
We propose to learn a probabilistic motion model from a sequence of images for spatio-temporal registration. Our model encodes motion in a low-dimensional probabilistic space - the motion matrix - which enables various motion analysis tasks such as simulation and interpolation of realistic motion patterns allowing for faster data acquisition and data augmentation. More precisely, the motion matrix allows to transport the recovered motion from one subject to another simulating for example a pathological motion in a healthy subject without the need for inter-subject registration. The method is based on a conditional latent variable model that is trained using amortized variational inference. This unsupervised generative model follows a novel multivariate Gaussian process prior and is applied within a temporal convolutional network which leads to a diffeomorphic motion model. Temporal consistency and generalizability is further improved by applying a temporal dropout training scheme. Applied to cardiac cine-MRI sequences, we show improved registration accuracy and spatio-temporally smoother deformations compared to three state-of-the-art registration algorithms. Besides, we demonstrate the model's applicability for motion analysis, simulation and super-resolution by an improved motion reconstruction from sequences with missing frames compared to linear and cubic interpolation.