Abstract

Deformable models integrate bottom-up information derived from image appearance cues and top-down priori knowledge of the shape. They have been widely used with success in medical image analysis. One limitation of traditional deformable models is that the information extracted from the image data may contain gross errors, which adversely affect the deformation accuracy. To alleviate this issue, we introduce a new family of deformable models that are inspired from the compressed sensing, a technique for accurate signal reconstruction by harnessing some sparseness priors. In this paper, we employ sparse regularization to handle the outliers or gross errors, and integrate it seamlessly with deformable models. The proposed new formulation is applied to the analysis of cardiac motion using tagged magnetic resonance imaging (tMRI), where the automated tagging line tracking results are very noisy due to the poor image quality. Our new deformable models track the heart motion robustly, and the resulting strains are consistent with those calculated from manual labels.

Downloads

• Blood flow simulation 1
• Blood flow simulation 2

BibTeX

@incollection{
year={2013},
booktitle={Information Processing in Medical Imaging},
volume={7917},
series={Lecture Notes in Computer Science},
editor={Gee, JamesC. and Joshi, Sarang and Pohl, KilianM. and Wells, WilliamM. and Zollei, Lilla},
title={Sparse Deformable Models with Application to Cardiac Motion Analysis},
publisher={Springer Berlin Heidelberg},
author={Yu, Yang and Zhang, Shaoting and Huang, Junzhou and Metaxas, Dimitris and Axel, Leon},
pages={208-219}
}

@incollection{Kulp_MICCAI11,
year={2011},
booktitle={Medical Image Computing and Computer-Assisted Intervention},
volume={6891},
series={Lecture Notes in Computer Science},
editor={Fichtinger, Gabor and Martel, Anne and Peters, Terry},
title={Using High Resolution Cardiac CT Data to Model and Visualize Patient-Specific Interactions between Trabeculae and Blood Flow},
publisher={Springer Berlin Heidelberg},
author={Kulp, Scott and Gao, Mingchen and Zhang, Shaoting and Qian, Zhen and Voros, Szilard and Metaxas, Dimitris and Axel, Leon},
pages={468-475}
}

Relevant publications

Yang Yu, Shaoting Zhang, Junzhou Huang, Dimitris Metaxas, Leon Axel: Sparse Deformable Models with Application to Cardiac Motion Analysis. IPMI 2013.

Yang Yu, Shaoting Zhang, Zhennan Yan, Song Chen, Rong Zhou, Dimitris Metaxas: Mouse LV 3D Motion and Strain Analysis using Tagged MRI. ISBI 2013. oral presentation

Scott Kulp, Mingchen Gao, Shaoting Zhang, Zhen Qian, Szilard Voros, Leon Axel and Dimitris Metaxas: Using High Resolution Cardiac CT Data to Model and Visualize Patient-Specific Interactions Between Trabeculae and Blood Flow. MICCAI, 2011.