A statistical model-based approach for the automatic quantitative analysis of perfusion gated SPECT studies

Sebastian Ordas; Santiago Aguade; Joan Castell; Alejandro F. Frangi

doi:10.1117/12.595897

14 April 2005 A statistical model-based approach for the automatic quantitative analysis of perfusion gated SPECT studies

Sebastian Ordas, Santiago Aguade, Joan Castell, Alejandro F. Frangi

Author Affiliations +

Proceedings Volume 5746, Medical Imaging 2005: Physiology, Function, and Structure from Medical Images; (2005) https://doi.org/10.1117/12.595897
Event: Medical Imaging, 2005, San Diego, California, United States

Abstract

In this paper we present a statistical model-based approach to three-dimensional (3D) analysis of gated SPECT perfusion studies. By means of a 3D Active Shape Model (3D-ASM) segmentation algorithm, delineations of the endo- and epicardial borders of the left ventricle are obtained, in all temporal phases and image slices of the study. Prior knowledge was captured from a training set of cardiac MRI and SPECT studies, from which geometrical (shape) and grey-level (appearance) statistical models were built. From the fitted shape, a truly 3D representation of the left ventricle, a series of global and regional functional parameters can be assessed. A myocardial center surface representation is built on top of which scalar maps of perfusion, thickness or motion can be depicted. Preliminary results were quite encouraging, suggesting that statistical model-based segmentation may serve as a robust technique for routine use.

Citation Download Citation

Sebastian Ordas, Santiago Aguade, Joan Castell, and Alejandro F. Frangi "A statistical model-based approach for the automatic quantitative analysis of perfusion gated SPECT studies", Proc. SPIE 5746, Medical Imaging 2005: Physiology, Function, and Structure from Medical Images, (14 April 2005); https://doi.org/10.1117/12.595897

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available