A Spatio-temporal Analysis of Contrast Ultrasound Image Sequences for Assessment of Tissue Perfusion
Lists
Only you see this
Abstract
The evaluation of tissue perfusion in various parenchymatous organs is important in the diagnosis and determination of the severity of ischemic disease. Contrast ultrasound perfusion imaging can be used for this purpose. This paper describes a method that identifies different areas of perfusion in a contrast ultrasound perfusion study. Pixels in an image sequence are automatically classified into different classes, by analysing their distinct temporal relationships. A novel method is presented that uses a Bayesian Factor Analysis Model set in a Markov Random Field framework; utilising both the temporal and spatial characteristics of the pixels for classification. Preliminary results are demonstrated for simulated data, and a myocardial perfusion in-vivo dataset.
BibTeX
@inproceedings{williams2004spatio,
author = {Quentin R. Williams and J. Alison Noble},
title = {{A Spatio-temporal Analysis of Contrast Ultrasound Image Sequences for Assessment of Tissue Perfusion}},
booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
year = {2004},
doi = {10.1007/978-3-540-30136-3\_109},
}| Myocardial Perfusion Classification Using A Markov Random Field Constrained Gaussian Mixture Model | Proceedings of the International Conference on Statistics, Theory and Applications (icsta ...) · 2022 |
| Quantification of Myocardial Perfusion Lesions using Spatially Variant Finite Mixture Modelling of DCE-MRI | Proceedings of the International Conference on Statistics, Theory and Applications (icsta ...) · 2019 |
| A Deep Learning Framework for Spatiotemporal Ultrasound Localization Microscopy | arXiv · 2023 |
| Spatio-temporal nonrigid registration for ultrasound cardiac motion estimation | IEEE TMI · 2005 |
| A Comprehensive 3-D Framework for Automatic Quantification of Late Gadolinium Enhanced Cardiac Magnetic Resonance Images | arXiv · 2022 |
| Perfusion Imaging: A Data Assimilation Approach | arXiv · 2020 |