Probabilistic Motion Modeling from Medical Image Sequences: Application to Cardiac Cine-MRI
This work addresses motion modeling challenges in medical imaging for cardiac analysis, offering incremental improvements in registration and simulation tasks.
The paper tackles the problem of learning probabilistic motion models from medical image sequences, specifically for cardiac cine-MRI, resulting in improved registration accuracy and smoother deformations compared to state-of-the-art methods, with applications in motion prediction and simulation.
We propose to learn a probabilistic motion model from a sequence of images. Besides spatio-temporal registration, our method offers to predict motion from a limited number of frames, useful for temporal super-resolution. The model is based on a probabilistic latent space and a novel temporal dropout training scheme. This enables simulation and interpolation of realistic motion patterns given only one or any subset of frames of a sequence. The encoded motion also allows to be transported from one subject to another without the need of inter-subject registration. An unsupervised generative deformation model is applied within a temporal convolutional network which leads to a diffeomorphic motion model, encoded as a low-dimensional motion matrix. 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 to motion transport by simulating a pathology in a healthy case. Furthermore, we show an improved motion reconstruction from incomplete sequences compared to linear and cubic interpolation.