# MRI-CT phantom registration

**URL:** https://discourse.itk.org/t/mri-ct-phantom-registration/7598
**Category:** Beginner Questions
**Tags:** registration
**Created:** [July 22, 2025, 2:09am UTC](https://discourse.itk.org/t/mri-ct-phantom-registration/7598 "2025-07-22T02:09:10Z")
**Posts on this page:** 4
**Page:** 1

<div class="post-metadata">

### Author: ![rohit\_inippully](https://discourse.itk.org/user_avatar/discourse.itk.org/rohit_inippully/32/2056_2.png) [@rohit\_inippully](https://discourse.itk.org/u/rohit_inippully)
#### Post date: [July 22, 2025, 2:09am UTC](https://discourse.itk.org/t/mri-ct-phantom-registration/7598/1 "2025-07-22T02:09:10Z")

</div>

![image](https://discourse.itk.org/uploads/default/original/2X/b/bd79214be85991f9f5c9ee638fc81a0421437f17.jpeg)

I am trying to register (rigid) a MRI image of a phantom to its CT image. However, I am not getting the results I need. I am using MattesMutual Metric, and regularstepgradient, Euler3DTransform, etc. Has anyone encountered similar problem and solved it?

Here is the code:

> **[GitHub - Rohit9987/MRI\_registration: MRI registration project for distortion correction](https://github.com/Rohit9987/MRI_registration)**
>
> MRI registration project for distortion correction

Thank you,

---

<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: [July 22, 2025, 1:02pm UTC](https://discourse.itk.org/t/mri-ct-phantom-registration/7598/2 "2025-07-22T13:02:17Z")

</div>

It looks like repetitive grid pattern quickly puts the registration metric into a local minimum. This could benefit from multi-resolution approach, especially with a lot of initial downsampling.

---

<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: [July 22, 2025, 1:04pm UTC](https://discourse.itk.org/t/mri-ct-phantom-registration/7598/3 "2025-07-22T13:04:32Z")

</div>

I just took a quick look at your source code. It looks like you are using some multi-resolution. Try using about 10 levels instead of 3.

---

<div class="post-metadata">

### Author: ![cookpa](https://discourse.itk.org/user_avatar/discourse.itk.org/cookpa/32/255_2.png) [@cookpa](https://discourse.itk.org/u/cookpa)
#### Post date: [July 22, 2025, 1:46pm UTC](https://discourse.itk.org/t/mri-ct-phantom-registration/7598/4 "2025-07-22T13:46:00Z")

</div>

Is the initialization good? It looks from your code that you’ve scaled the CT to be positive, which is a good start, but it’s worth doing a visual check of where the optimization is starting from.