Unsupervised Myocardial Segmentation for Cardiac MRI
Though unsupervised segmentation was a de-facto standard for cardiac MRI segmentation early on, recently cardiac MRI segmentation literature has favored fully supervised techniques such as Dictionary Learning and Atlas-based techniques. But, the benefits
- PDF / 465,407 Bytes
- 9 Pages / 439.363 x 666.131 pts Page_size
- 107 Downloads / 206 Views
2
IMT Institute for Advanced Studies Lucca, Italy Biomedical Imaging Research Institute, Cedars-Sinai Medical, Los Angeles, USA 3 Department of Electrical Engineering and Computer Science, Northwestern University, Evanston, USA
Abstract. Though unsupervised segmentation was a de-facto standard for cardiac MRI segmentation early on, recently cardiac MRI segmentation literature has favored fully supervised techniques such as Dictionary Learning and Atlas-based techniques. But, the benefits of unsupervised techniques e.g., no need for large amount of training data and better potential of handling variability in anatomy and image contrast, is more evident with emerging cardiac MR modalities. For example, CP-BOLD is a new MRI technique that has been shown to detect ischemia without any contrast at stress but also at rest conditions. Although CP-BOLD looks similar to standard CINE, changes in myocardial intensity patterns and shape across cardiac phases, due to the heart’s motion, BOLD effect and artifacts affect the underlying mechanisms of fully supervised segmentation techniques resulting in a significant drop in segmentation accuracy. In this paper, we present a fully unsupervised technique for segmenting myocardium from the background in both standard CINE MR and CP-BOLD MR. We combine appearance with motion information (obtained via Optical Flow) in a dictionary learning framework to sparsely represent important features in a low dimensional space and separate myocardium from background accordingly. Our fully automated method learns background-only models and one class classifier provides myocardial segmentation. The advantages of the proposed technique are demonstrated on a dataset containing CP-BOLD MR and standard CINE MR image sequences acquired in baseline and ischemic condition across 10 canine subjects, where our method outperforms state-of-the-art supervised segmentation techniques in CP-BOLD MR and performs at-par for standard CINE MR. Keywords: Unsupervised Segmentation, Dictionary Learning, BOLD, CINE, MRI.
1
Introduction
Cardiovascular Disease (CVD) is the leading cause of mortality worldwide, and the modern analysis of cardiac function using imaging techniques (specifically c Springer International Publishing Switzerland 2015 N. Navab et al. (Eds.): MICCAI 2015, Part III, LNCS 9351, pp. 12–20, 2015. DOI: 10.1007/978-3-319-24574-4_2
Unsupervised Myocardial Segmentation for Cardiac MRI
13
Cardiac CINE MR) is an effective way of diagnosing CVD. An emerging cinelike cardiac modality is Cardiac Phase-resolved Blood Oxygen-Level-Dependent (CP-BOLD) MR, a truly noninvasive method that identifies the ischemic myocardium by examining changes in myocardial signal intensity patterns as a function of cardiac phase [19]. Fully supervised myocardial segmentation (i.e., separating myocardium from the rest of the anatomy) developed for standard CINE MR, however, underperform in the case of CP-BOLD MR due to the spatio-temporal intensity variations of the myocardial BOLD effect [14,19]. Thus, in addition to violating
Data Loading...
