Key result
An automatic approach for segmenting the left atrium from MR images via variational region growing with a moments-based shape prior demonstrated robustness and accuracy on 64 human MR images.
Why the study?
Does an automatic segmentation approach using variational region growing with a moments-based shape prior improve the segmentation of the left atrium from MR images?
Does an automatic segmentation approach using variational region growing with a moments-based shape prior improve the segmentation of the left atrium from MR images?
The proposed automatic segmentation approach using variational region growing with a moments-based shape prior demonstrates robustness and accuracy in segmenting the left atrium from MR images.
Offers a proof-of-concept for automated LA assessment; leaves open whether this algorithm improves clinical workflow.
The planning and evaluation of left atrial ablation procedures are commonly based on the segmentation of the left atrium, which is a challenging task due to large anatomical variations. In this paper, we propose an automatic approach for segmenting the left atrium from magnetic resonance imagery. The segmentation problem is formulated as a problem in variational region growing. In particular, the method starts locally by searching for a seed region of the left atrium from an MR slice. A global constraint is imposed by applying a shape prior to the left atrium represented by Zernike moments. The overall growing process is guided by the robust statistics of intensities from the seed region along with the shape prior to capture the entire atrial region. The robustness and accuracy of our approach are demonstrated by experimental results from 64 human MR images.
No takes yet. Share an insight, caveat, or question.
Zhu et al. (2013) studied Left atrial segmentation for ablation planning (n=64). Automatic segmentation via variational region growing with a moments-based shape prior was evaluated on Robustness and accuracy of segmentation. An automatic approach for segmenting the left atrium from MR images via variational region growing with a moments-based shape prior demonstrated robustness and accuracy on 64 human MR images.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: