Classification of Myocardial Blood Flow based on Dynamic Contrast-Enhanced Magnetic Resonance Imaging using Hierarchical Bayesian Models

Abstract

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a promising approach to assess microvascular blood flow (perfusion) within the myocardium, and the Fermi microvascular perfusion model is widely applied to extract estimates of the myocardial blood flow (MBF) from DCE-MRI data sets. The classification of myocardial tissues into normal (healthy) and hypoperfused (lesion) regions provides new opportunities for the diagnosis of coronary heart disease and for advancing our understanding of the aetiology of this highly prevalent disease. In the present paper, the Fermi model is combined with a hierarchical Bayesian model (HBM) and a Markov random fields prior to automate this classification. The proposed model exploits spatial context information to smooth the MBF estimates while sharpening the edges between lesions and healthy tissues. The model parameters are approximately sampled from the posterior distribution with Markov chain Monte Carlo (MCMC), and we demonstrate that this enables robust classification of myocardial tissue elements based on This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Myocardial Perfusion Classification Using A Markov Random Field Constrained Gaussian Mixture Model

“…The synthetic data is designed to mimic the clinical data used in this work. Similarly, for easier comparison, the synthetic data is also consistent with the data generated in [5]. A summary of the design is illustrated here.…”

“…The mid slice of the myocardial perfusion DCE-MRI data is used to estimate the MBF by the Fermi method [2]. The choice of the clinical data is consistent with the clinical data used in [5] for easier comparisons.…”

“…However, a main shortcoming of the GMM classification method for myocardial perfusion DCE-MRI is that its classification map contains physiologically unrealistic small and even singular clusters [4]. Spatial prior information has been incorporated to address this issue in [4,5] using a spatial variant finite mixture model (SVFMM) and hierarchical Bayesian model (HBM). However, the method proposed in [4] only reduces the number of small and singular clusters (rather than eliminate them altogether), and the method proposed in [5] is computationally expensive.…”

“…Spatial prior information has been incorporated to address this issue in [4,5] using a spatial variant finite mixture model (SVFMM) and hierarchical Bayesian model (HBM). However, the method proposed in [4] only reduces the number of small and singular clusters (rather than eliminate them altogether), and the method proposed in [5] is computationally expensive. Therefore, the main aim of the proposed method is to develop a fast and effective classification method based on the estimated MBF map.…”

“…In this work, the proposed method has been applied to and assessed on both synthetic and clinical data. We have used GMM and HBM, proposed in [5], as benchmark methods for comparison. Section 2 describes the statistical model.…”