Skip to Main content Skip to Navigation
Conference papers

Dense Motion Estimation of the Heart Based on Cumulants

Abstract : Mutual Information (MI) has been extensively studied as similarity measure for the registration of medical images, and it has been found to be especially robust for multimodal image registration. However, MI estimators are known i) to have a very high variance and ii) to be computationally costly. In order to overcome these drawbacks, we propose a new similarity measure based on the sum of squared cumulants. In addition, our measure can be easily derivated with respect to registration parameters leading to an optimization with a simple gradient rule. Such a scheme is presented for a non-rigid registration and its performance is studied through computer results in the context of cardiac multislice computed tomography
Complete list of metadata

Cited literature [10 references]  Display  Hide  Download
Contributor : Lotfi Senhadji Connect in order to contact the contributor
Submitted on : Sunday, October 31, 2010 - 10:28:50 AM
Last modification on : Thursday, March 31, 2022 - 3:40:47 AM
Long-term archiving on: : Tuesday, February 1, 2011 - 11:03:24 AM


Files produced by the author(s)


  • HAL Id : inserm-00530929, version 1


Mathieu Rubeaux, Jean-Claude Nunes, Laurent Albera, Mireille Garreau. Dense Motion Estimation of the Heart Based on Cumulants. Computers In Cardiology, Sep 2009, Park City, UT, United States. pp.609 - 612. ⟨inserm-00530929⟩



Record views


Files downloads