Conference Paper

Early detection of rejection in cardiac MRI: a spectral graph approach

Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA
DOI: 10.1109/ISBI.2006.1624865 Conference: Proceedings of the 2006 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Arlington, VA, USA, 6-9 April 2006
Source: IEEE Xplore


This paper develops an algorithm to detect abnormalities of small animals' transplanted hearts in MRI, at early stage of rejection when the hearts do not display prominent abnormal features. Existing detection methods require experts to manually identify these abnormal regions. This task is time consuming, and the detection criteria are operator dependent. We present a semi-automatic approach that needs experts to label only a small portion of the motion maps. Our algorithm begins with representing the left ventricular motions by a weighted graph that approximates the manifold where these motions lie. We compute the eigendecomposition of the Laplacian of the graph and use these as basis functions to represent the classifier. The experimental results with synthetic data and real cardiac MRI data demonstrate the application of our classifier to early detection of heart rejection

Download full-text


Available from: Jose M F Moura
  • Source
    • "Since graphs are often used for detection of anomolous occurrences or behavior, such problems could be presented in the context of classical detection theory. Indeed, [16] [17] [18] present detection problems using graphical data and evaluate their techniques with metrics common in signal processing, such as receiver operating characteristic (ROC) analysis. These problems all have a similar underlying structure: Given a graph G, we want to find GS ⊂ G such that GS is anomolous, dense or equal to some template. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Graphs are canonical examples of high-dimensional non-Euclidean data sets, and are emerging as a common data structure in many fields. While there are many algorithms to analyze such data, a signal processing theory for evaluating these techniques akin to detection and estimation in the classical Euclidean setting remains to be developed. In this paper we show the conceptual advantages gained by formulating graph analysis problems in a signal processing framework by way of a practical example: detection of a subgraph embedded in a background graph. We describe an approach based on detection theory and provide empirical results indicating that the test statistic proposed has reasonable power to detect dense subgraphs in large random graphs.
    Preview · Conference Paper · Apr 2010
  • Source
    • "In [2], we proposed a computer assisted method to detect regional heart malfunction based on spectral graph theory [3] [4] [5]. The classifier in [2] is semisupervised—initially, a human expert labels as normal or abnormal a small portion of the motions and then the classifier propagates the human prior knowledge to the remaining unlabeled motions. In early stages of heart disease, the abnormal motions are not prominent . "
    [Show abstract] [Hide abstract]
    ABSTRACT: Magnetic resonance (MR) tagging technology can assist us in determining the motions of the myocardial pixels in a sequence of MR images. This paper presents a semi-supervised algorithm that processes these motion maps and classifies automatically myocardial dysfunctional motions. In distinction with other methods, our algorithm requires that only a few normal motions are labeled a priori. This is significant because, while normal motions can be confidently labeled by a human expert, abnormal motions are very difficult to label with high reliability by an operator. We use a graph to capture the motion map of the left ventricle. The normalized weighted adjacency matrix of the graph is interpreted as a stochastic matrix. Performing random walks, or diffusion, on the graph determines how similar myocardial motions are. Similar motions on the graph are represented by the diffusion maps framework as closer vectors in a Euclidean space. In the Euclidean space, we adopt eigen-analysis on a small portion of labeled normal motions. The analysis leads to a hyperelliptic surface that classifies the remaining cardiac motions as normal or dysfunctional.
    Full-text · Conference Paper · Sep 2007
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we analyse mathematical properties of spatial optical-flow computation algorithm. First by numerical analysis, we derive the convergence property on variational optical-flow computation method used for cardiac motion detection. From the convergence property of the algorithm, we clarify the condition for the scheduling of the regularisation parameters. This condition shows that for the accurate and stable computation with scheduling the regularisation coefficients, we are required to control the sampling interval for numerical computation.
    Full-text · Conference Paper · Aug 2007
Show more