Logo image
Back
Deep Generative Storm Model for Dynamic Imaging
Conference proceeding

Deep Generative Storm Model for Dynamic Imaging

Qing Zou, Abdul Haseeb Ahmed, Prashant Nagpal, Stanley Kruger and Mathews Jacob
2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp.114-117
04/13/2021
DOI: 10.1109/ISBI48211.2021.9433839
PMCID: PMC8320670
PMID: 34336134
url
https://www.ncbi.nlm.nih.gov/pmc/articles/8320670View
Open Access

Abstract

We introduce a novel generative smoothness regularization on manifolds (SToRM) model for the recovery of dynamic image data from highly undersampled measurements. The proposed generative framework represents the image time series as a smooth non-linear function of low-dimensional latent vectors that capture the cardiac and respiratory phases. The nonlinear function is represented using a deep convolutional neural network (CNN). Unlike the popular CNN approaches that require extensive fully-sampled training data that is not available in this setting, the parameters of the CNN generator as well as the latent vectors are jointly estimated from the undersampled measurements using stochastic gradient descent. We penalize the norm of the gradient of the generator to encourage the learning of a smooth surface/manifold, while temporal gradients of the latent vectors are penalized to encourage the time series to be smooth. The main benefits of the proposed scheme are (a) the quite significant reduction in memory demand compared to the analysis based SToRM model, and (b) the spatial regularization brought in by the CNN model. We also introduce efficient progressive approaches to minimize the computational complexity of the algorithm.
 Time Series Analysis Manifolds Storms Computational modeling Heuristic algorithms Training data Biomedical measurement

Details

Metrics

19 Record Views
5 Times Cited - Web of Science
Logo image