Spatial Correspondence between Graph Neural Network-Segmented Images

by   Qian Li, et al.
Harbin Institute of Technology

Graph neural networks (GNNs) have been proposed for medical image segmentation, by predicting anatomical structures represented by graphs of vertices and edges. One such type of graph is predefined with fixed size and connectivity to represent a reference of anatomical regions of interest, thus known as templates. This work explores the potentials in these GNNs with common topology for establishing spatial correspondence, implicitly maintained during segmenting two or more images. With an example application of registering local vertebral sub-regions found in CT images, our experimental results showed that the GNN-based segmentation is capable of accurate and reliable localization of the same interventionally interesting structures between images, not limited to the segmentation classes. The reported average target registration errors of 2.2±1.3 mm and 2.7±1.4 mm, for aligning holdout test images with a reference and for aligning two test images, respectively, were by a considerable margin lower than those from the tested non-learning and learning-based registration algorithms. Further ablation studies assess the contributions towards the registration performance, from individual components in the originally segmentation-purposed network and its training algorithm. The results highlight that the proposed segmentation-in-lieu-of-registration approach shares methodological similarities with existing registration methods, such as the use of displacement smoothness constraint and point distance minimization albeit on non-grid graphs, which interestingly yielded benefits for both segmentation and registration. We, therefore, conclude that the template-based GNN segmentation can effectively establish spatial correspondence in our application, without any other dedicated registration algorithms.


page 3

page 7

page 17


MvMM-RegNet: A new image registration framework based on multivariate mixture model and neural network estimation

Current deep-learning-based registration algorithms often exploit intens...

Conditional Segmentation in Lieu of Image Registration

Classical pairwise image registration methods search for a spatial trans...

Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registration

One of the fundamental challenges in supervised learning for multimodal ...

Locate, Segment and Match: A Pipeline for Object Matching and Registration

Image registration requires simultaneous processing of multiple images t...

Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registration

The prowess that makes few-shot learning desirable in medical image anal...

Few-shot image segmentation for cross-institution male pelvic organs using registration-assisted prototypical learning

The ability to adapt medical image segmentation networks for a novel cla...

Please sign up or login with your details

Forgot password? Click here to reset