# registration of histological hne image on segmentation label.

**URL:** <https://discourse.itk.org/t/registration-of-histological-hne-image-on-segmentation-label/5659>\
**Category:** Uncategorized\
**Created:** [January 30, 2023, 8:09pm UTC](https://discourse.itk.org/t/registration-of-histological-hne-image-on-segmentation-label/5659 "2023-01-30T20:09:54Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![banikr](https://discourse.itk.org/user_avatar/discourse.itk.org/banikr/32/3296_2.png) [@banikr](https://discourse.itk.org/u/banikr)\
**Post date:** [January 30, 2023, 8:09pm UTC](https://discourse.itk.org/t/registration-of-histological-hne-image-on-segmentation-label/5659/1 "2023-01-30T20:09:54Z")

</div>

Hello,  
I am trying to register a high resolution H & E stained image(RGB) on a segmentation image.  
The RGB image size is: (620, 734, 3)  
and label image is: (96, 73)

The problems are:

1. Is it possible to register 3 channel RGB image on the label map? In this case shall grayscale image be used or taking a single channel from the RGB?
2. what kind of resampling, spacing, and dimension of both fixed(label) and moving(hne) should be considered?

I have uploaded the demo data here:  
[hne\_label.mat](https://discourse.itk.org/uploads/short-url/3f919F1BcsQQw15wHh80t3TS2tT.mat) (1.4 MB)

---

<div class="post-metadata">

**Author:** ![dzenanz](https://discourse.itk.org/user_avatar/discourse.itk.org/dzenanz/32/1093_2.png) [@dzenanz](https://discourse.itk.org/u/dzenanz)\
**Post date:** [January 30, 2023, 8:56pm UTC](https://discourse.itk.org/t/registration-of-histological-hne-image-on-segmentation-label/5659/2 "2023-01-30T20:56:29Z")

</div>

That is a strange problem. Segmentations are usually done using some “feature” image as a reference. And you register feature images, and apply the resulting transform on the segmentation.

Using information from multiple channels during registration is hard. I suggest converting your RGB image into grayscale.

Before writing any code, I suggest using [Slicer](https://www.slicer.org/), and its BRAINS and Elastix registration modules to experiment.

---

<div class="post-metadata">

**Author:** ![banikr](https://discourse.itk.org/user_avatar/discourse.itk.org/banikr/32/3296_2.png) [@banikr](https://discourse.itk.org/u/banikr)\
**Post date:** [January 30, 2023, 9:10pm UTC](https://discourse.itk.org/t/registration-of-histological-hne-image-on-segmentation-label/5659/3 "2023-01-30T21:10:11Z")

</div>

The segmentation map/image comes from a different modality. And I am trying to fuse both of them into the same space. That is why I am trying to register hne on label. Also not having an atlas makes more problematic.