Yang, Y., Husmeier, D. , Gao, H. , Berry, C. , Carrick, D. and Radjenovic, A. (2024) Automatic detection of myocardial ischaemia using generalisable spatio-temporal hierarchical Bayesian modelling of DCE-MRI. Computerized Medical Imaging and Graphics, 113, 102333. (doi: 10.1016/j.compmedimag.2024.102333) (PMID:38281420)
![[img]](https://eprints.gla.ac.uk/style/images/fileicons/text.png) |
Text
316488.pdf - Published Version Available under License Creative Commons Attribution. 2MB |
Abstract
Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) can be used as a non-invasive method for the assessment of myocardial perfusion. The acquired images can be utilized to analyze the spatial extent and severity of myocardial ischaemia (regions with impaired microvascular blood flow). In the present paper, we propose a novel generalisable spatio-temporal hierarchical Bayesian model (GST-HBM) to automate the detection of ischaemic lesions and improve the in silico prediction accuracy by systematically integrating spatio-temporal context information. We present a computational inference procedure with an adequate trade-off between accuracy and computational efficiency, whereby model parameters are sampled from the posterior distribution with Gibbs sampling, while lower-level hyperparameters are selected using model selection strategies based on the Watanabe Akaike information criterion (WAIC). We have assessed our method on both synthetic (in silico) data with known gold-standard and 12 sets of clinical first-pass myocardial perfusion DCE-MRI datasets. We have also carried out a comparative performance evaluation with four established alternative methods: Gaussian mixture model (GMM), opening and closing operations based on Gaussian mixture model (GMM maxC&O), Markov random field constrained Gaussian mixture model (GMM-MRF) and model-based hierarchical Bayesian model (M-HBM). Our results show that the proposed GST-HBM method achieves much higher in silico prediction accuracy than the established alternative methods. Furthermore, this method appears to provide a more robust delineation of ischaemic lesions in datasets affected by spatially variant noise.
| Item Type: | Articles |
|---|---|
| Additional Information: | This work was funded by the UK Engineering and Physical Sciences Research Council (EPSRC), grant reference numbers EP/S020950/1, EP/S030875/1 and EP/T017899/1. Yalei Yang and Aleksandra Radjenovic are funded by a grant from GlaxoSmithKline R&D. Colin Berry is supported by the British Heart Foundation (RE/18/6134217). |
| Keywords: | hierarchical Bayesian models, spatio-temporal Markov random fields, first pass myocardial perfusion DCE-MRI, myocardial hypoperfusion, myocardial ischaemia, Gibbs sampling, model selection, Watanabe Akaike information criterion. |
| Status: | Published |
| Refereed: | Yes |
| Glasgow Author(s) Enlighten ID: | Berry, Professor Colin and Gao, Dr Hao and Yang, Dr Yalei and Husmeier, Professor Dirk and Radjenovic, Dr Aleksandra |
| Authors: | Yang, Y., Husmeier, D., Gao, H., Berry, C., Carrick, D., and Radjenovic, A. |
| College/School: | College of Medical Veterinary and Life Sciences > School of Cardiovascular & Metabolic Health College of Science and Engineering > School of Mathematics and Statistics College of Science and Engineering > School of Mathematics and Statistics > Mathematics College of Science and Engineering > School of Mathematics and Statistics > Statistics |
| Journal Name: | Computerized Medical Imaging and Graphics |
| Publisher: | Elsevier |
| ISSN: | 0895-6111 |
| ISSN (Online): | 1879-0771 |
| Published Online: | 11 January 2024 |
| Copyright Holders: | Copyright © 2024 The Authors |
| First Published: | First published in Computerized Medical Imaging and Graphics 113:102333 |
| Publisher Policy: | Reproduced under a Creative Commons License |
University Staff: Request a correction | Enlighten Editors: Update this record
Funder and Project Information
Funder and Project Information