Learning a Generative Motion Model From Image Sequences Based on a Latent Motion Matrix

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 pa...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on medical imaging Jg. 40; H. 5; S. 1405 - 1416
Hauptverfasser: Krebs, Julian, Delingette, Herve, Ayache, Nicholas, Mansi, Tommaso
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.05.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Institute of Electrical and Electronics Engineers
Schlagworte:
Algorithms
Artificial Intelligence
Computer Science
Computer Vision and Pattern Recognition
conditional variational autoencoder
Data acquisition
Data models
Deformable models
deformable registration
Gaussian process
Gaussian processes
Humans
Image Processing, Computer-Assisted
Image sequences
Interpolation
latent variable model
Machine Learning
Magnetic Resonance Imaging
Magnetic Resonance Imaging, Cine
Medical Imaging
Motion
motion interpolation
Motion model
motion simulation
Probabilistic logic
Registration
Simulation
Strain
Tracking
motion simulation
conditional variational autoencoder
latent variable model
motion model
tracking
deformable registration
motion interpolation
gaussian process
ISSN:0278-0062, 1558-254X, 1558-254X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0278-0062
1558-254X
1558-254X
DOI:10.1109/TMI.2021.3056531