Cardiac Image Super-Resolution with Global Correspondence Using Multi-Atlas PatchMatch

Abstract

Abstract. The accurate measurement of 3D cardiac function is an important task in the analysis of cardiac magnetic resonance (MR) images. However, short-axis image acquisitions with thick slices are commonly used in clinical practice due to constraints of acquisition time, signal-tonoise ratio and patient compliance. In this situation, the estimation of a high-resolution image can provide an approximation of the underlaying 3D measurements. In this paper, we develop a novel algorithm for the estimation of high-resolution cardiac MR images from single short-axis cardiac MR image stacks. First, we propose to use a novel approximate global search approach to find patch correspondence between the shortaxis MR image and a set of atlases. Then, we propose an innovative super-resolution model which does not require explicit motion estimation. Finally, we build an expectation-maximization framework to optimize the model. We validate the proposed approach using images from 19 subjects with 200 atlases and show that the proposed algorithm significantly outperforms conventional interpolation such as linear or B-spline interpolation. In addition, we show that the super-resolved images can be used for the reproducible estimation of 3D cardiac functional indices.

A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion

“…Multi-atlas segmentation has been demonstrated as a robust and accurate segmentation method for brain and cardiac images in the recent years (Asman and Landman, 2013;Bai et al, 2013;Wang et al, 2013). In this work, we use the multi-atlas PatchMatch algorithm for cardiac image segmentation (de Marvao et al, 2014;Shi et al, 2013a).…”

“…The multi-atlas segmentation algorithm then goes across each image patch in the input image, looks for similar image patches in the atlas images and assigns the labels of the atlas image patches onto the input image with confidence weights, forming the segmentation result. Detail of the multi-atlas segmentation method can be referred to at (de Marvao et al, 2014;Shi et al, 2013a). Except from defining the six landmarks, all the other steps are automatic for segmentation.…”

Regional ejection fraction and regional area strain for left ventricular function assessment in male patients after first-time myocardial infarction

“…Automatic image segmentation techniques [32,33] could be explored to speed up the manual segmentation process. Other segmentation techniques such as shape-based interpolation [34] and superresolution [35,36] can also be potentially used to automate and increase the accuracy of the cardiac segmentation. The deployment of such an automated segmentation algorithm will allow our computation of the REF and RAS to be further speeded up as compared with our current approach.…”

UHD Video Super-Resolution Using Low-Rank and Sparse Decomposition

“…The recovery of high-resolution (HR) images and videos from low-resolutions (LR) content is a topic of great interest in digital image processing with applications in many areas such as HDTV [11], medical imaging [20], satellite imaging [23], face recognition [12], immersive content generation, and surveillance [27]. The global super-resolution (SR) problem assumes that the LR image is a noisy, lowpass filtered, and downsampled version of the HR image.…”