InsightSoftwareConsortium / InsightSoftwareConsortium/ITKElastix

ErodeMask and dilating mask

Open
#286 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
281
Forks
29
Avg merge
16h 28m
Merged PRs (30d)
8

Description

In the Elastix documentations, there are mentions of dilating the fixed image mask when using the mask to focus the registration on an ROI, but it is not explained well. Perhaps the dilation is useful when we want to include the mask edge as part of the registration? For e.g., if the mask is a segmentation of the lung, we would like the lung edge to be part of the registration as it would help to match the lungs to match? If so, how important is it for the registration and how much should the dilation be? There is also the ErodeMask feature, when set to true, avoids artificial edges from influencing registration during multi resolution procedure. Does that mean dilating mask and ErodeMask perform the opposite function? One is intended to include the edges of the mask but the other intended to exclude them? Thanks!

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.