Unsupervised dynamic modeling of medical image transformation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gunnarsson, Niklas, Kimstrand, Peter, Sjölund, Jens, Schön, Thomas B.
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914971837792256
author Gunnarsson, Niklas
Kimstrand, Peter
Sjölund, Jens
Schön, Thomas B.
author_facet Gunnarsson, Niklas
Kimstrand, Peter
Sjölund, Jens
Schön, Thomas B.
contents Spatiotemporal imaging has applications in e.g. cardiac diagnostics, surgical guidance, and radiotherapy monitoring, In this paper, we explain the temporal motion by identifying the underlying dynamics, only based on the sequential images. Our dynamical model maps the inputs of observed high-dimensional sequential images to a low-dimensional latent space wherein a linear relationship between a hidden state process and the lower-dimensional representation of the inputs holds. For this, we use a conditional variational auto-encoder (CVAE) to nonlinearly map the higher-dimensional image to a lower-dimensional space, wherein we model the dynamics with a linear Gaussian state-space model (LG-SSM). The model, a modified version of the Kalman variational auto-encoder, is end-to-end trainable, and the weights, both in the CVAE and LG-SSM, are simultaneously updated by maximizing the evidence lower bound of the marginal likelihood. In contrast to the original model, we explain the motion with a spatial transformation from one image to another. This results in sharper reconstructions and the possibility of transferring auxiliary information, such as segmentation, through the image sequence. Our experiments, on cardiac ultrasound time series, show that the dynamic model outperforms traditional image registration in execution time, to a similar performance. Further, our model offers the possibility to impute and extrapolate for missing samples.
format Preprint
id arxiv_https___arxiv_org_abs_2103_00930
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Unsupervised dynamic modeling of medical image transformation
Gunnarsson, Niklas
Kimstrand, Peter
Sjölund, Jens
Schön, Thomas B.
Medical Physics
Computer Vision and Pattern Recognition
Machine Learning
Systems and Control
Image and Video Processing
Spatiotemporal imaging has applications in e.g. cardiac diagnostics, surgical guidance, and radiotherapy monitoring, In this paper, we explain the temporal motion by identifying the underlying dynamics, only based on the sequential images. Our dynamical model maps the inputs of observed high-dimensional sequential images to a low-dimensional latent space wherein a linear relationship between a hidden state process and the lower-dimensional representation of the inputs holds. For this, we use a conditional variational auto-encoder (CVAE) to nonlinearly map the higher-dimensional image to a lower-dimensional space, wherein we model the dynamics with a linear Gaussian state-space model (LG-SSM). The model, a modified version of the Kalman variational auto-encoder, is end-to-end trainable, and the weights, both in the CVAE and LG-SSM, are simultaneously updated by maximizing the evidence lower bound of the marginal likelihood. In contrast to the original model, we explain the motion with a spatial transformation from one image to another. This results in sharper reconstructions and the possibility of transferring auxiliary information, such as segmentation, through the image sequence. Our experiments, on cardiac ultrasound time series, show that the dynamic model outperforms traditional image registration in execution time, to a similar performance. Further, our model offers the possibility to impute and extrapolate for missing samples.
title Unsupervised dynamic modeling of medical image transformation
topic Medical Physics
Computer Vision and Pattern Recognition
Machine Learning
Systems and Control
Image and Video Processing
url https://arxiv.org/abs/2103.00930