Numerical Surrogates for Human Observers in Myocardial Motion Evaluation From SPECT Images

    Authors

    T. Marin; M. M. Kalayeh; F. M. Parages;J. G. Brankov

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    IEEE Trans. Med. Imaging

    Keywords

    Cardiac motion; cardiac-gated single photon emission computed; tomography; image quality; machine learning; model observers; numerical; observer; PERFUSION SPECT; LEFT-VENTRICLE; GATED SPECT; MATHEMATICAL-MODEL; HOTELLING OBSERVER; DETECTION ACCURACY; RECONSTRUCTION; COMPENSATION; OPTIMIZATION; QUANTITATION; Computer Science, Interdisciplinary Applications; Engineering, ; Biomedical; Engineering, Electrical & Electronic; Imaging Science &; Photographic Technology; Radiology, Nuclear Medicine & Medical Imaging

    Abstract

    In medical imaging, the gold standard for image-quality assessment is a task-based approach in which one evaluates human observer performance for a given diagnostic task (e. g., detection of a myocardial perfusion or motion defect). To facilitate practical task-based image-quality assessment, model observers are needed as approximate surrogates for human observers. In cardiac-gated SPECT imaging, diagnosis relies on evaluation of the myocardial motion as well as perfusion. Model observers for the perfusion-defect detection task have been studied previously, but little effort has been devoted toward development of a model observer for cardiac-motion defect detection. In this work, we describe two model observers for predicting human observer performance in detection of cardiac-motion defects. Both proposed methods rely on motion features extracted using previously reported deformable mesh model for myocardium motion estimation. The first method is based on a Hotelling linear discriminant that is similar in concept to that used commonly for perfusion-defect detection. In the second method, based on relevance vector machines (RVM) for regression, we compute average human observer performance by first directly predicting individual human observer scores, and then using multi reader receiver operating characteristic analysis. Our results suggest that the proposed RVM model observer can predict human observer performance accurately, while the new Hotelling motion-defect detector is somewhat less effective.

    Journal Title

    Ieee Transactions on Medical Imaging

    Volume

    33

    Issue/Number

    1

    Publication Date

    1-1-2014

    Document Type

    Article

    Language

    English

    First Page

    38

    Last Page

    47

    WOS Identifier

    WOS:000331296800004

    ISSN

    0278-0062

    Share

    COinS