VoteNet++: Registration Refinement for Multi-Atlas Segmentation

10/26/2020 ∙ by Zhipeng Ding, et al. ∙ 0 ∙ share

Multi-atlas segmentation (MAS) is a popular image segmentation technique for medical images. In this work, we improve the performance of MAS by correcting registration errors before label fusion. Specifically, we use a volumetric displacement field to refine registrations based on image anatomical appearance and predicted labels. We show the influence of the initial spatial alignment as well as the beneficial effect of using label information for MAS performance. Experiments demonstrate that the proposed refinement approach improves MAS performance on a 3D magnetic resonance dataset of the knee.

READ FULL TEXT

Learning Shape Representation on Sparse Point Clouds for Volumetric Image Segmentation

Volumetric image segmentation with convolutional neural networks (CNNs) ...
06/05/2019 ∙ by Fabian Balsiger, et al. ∙ 0 ∙ share

read it
Feature Sensitive Label Fusion with Random Walker for Atlas-based Image Segmentation

In this paper, a novel label fusion method is proposed for brain magneti...
10/24/2016 ∙ by Siqi Bao, et al. ∙ 0 ∙ share

read it
Learning Deformable Registration of Medical Images with Anatomical Constraints

Deformable image registration is a fundamental problem in the field of m...
01/20/2020 ∙ by Lucas Mansilla, et al. ∙ 13 ∙ share

read it
Quantifying and Leveraging Predictive Uncertainty for Medical Image Assessment

The interpretation of medical images is a challenging task, often compli...
07/08/2020 ∙ by Florin C. Ghesu, et al. ∙ 27 ∙ share

read it
Active Mean Fields for Probabilistic Image Segmentation: Connections with Chan-Vese and Rudin-Osher-Fatemi Models

Segmentation is a fundamental task for extracting semantically meaningfu...
01/22/2015 ∙ by Marc Niethammer, et al. ∙ 0 ∙ share

read it
Label-driven weakly-supervised learning for multimodal deformable image registration

Spatially aligning medical images from different modalities remains a ch...
11/05/2017 ∙ by Yipeng Hu, et al. ∙ 0 ∙ share

read it
An Optimized PatchMatch for Multi-scale and Multi-feature Label Fusion

Automatic segmentation methods are important tools for quantitative anal...
03/17/2019 ∙ by Remi Giraud, et al. ∙ 0 ∙ share

read it

VoteNet++: Registration Refinement for Multi-Atlas Segmentation

Authors

Learning Shape Representation on Sparse Point Clouds for Volumetric Image Segmentation

Feature Sensitive Label Fusion with Random Walker for Atlas-based Image Segmentation

Learning Deformable Registration of Medical Images with Anatomical Constraints

Quantifying and Leveraging Predictive Uncertainty for Medical Image Assessment

Active Mean Fields for Probabilistic Image Segmentation: Connections with Chan-Vese and Rudin-Osher-Fatemi Models

Label-driven weakly-supervised learning for multimodal deformable image registration

An Optimized PatchMatch for Multi-scale and Multi-feature Label Fusion

This week in AI