[ITK-users] New Submission: Learning Shape Representations for Multi-Atlas Endocardium Segmentation in 3D Echo Images

[MIDAS Journal]

Hello,

A new submission has been added to the MIDAS Journal.

Title: Learning Shape Representations for Multi-Atlas Endocardium Segmentation in 3D Echo Images
Authors: Oktay O., Shi W., Keraudren K., Caballero J., Rueckert D.
Abstract: As part of the CETUS challenge, we present a multi-atlas segmentation framework to delineate the left-ventricle endocardium in echocardiographic images. To increase the robustness of the registration step, we introduce a speckle reduction step and a new shape representation based on sparse coding and manifold approximation in dictionary
space. The shape representation, unlike intensity values, provides consistent shape information across different images. The validation results on the test set show that registration based on our shape representation significantly improves the performance of multi-atlas segmentation compared to intensity based registration. To our knowledge it is the first time that multi-atlas segmentation achieves state-of-the-art results for echocardiographic images.

Download and review this publication at: http://hdl.handle.net/10380/3486

Generated by the MIDAS Journal

You are receiving this email because you asked to be informed by the MIDAS Journal for new submissions. To change your email preference visit http://www.midasjournal.org/ .