# Plastimatch and Python Interactor

**URL:** <https://discourse.slicer.org/t/plastimatch-and-python-interactor/11556>\
**Category:** Support\
**Created:** [May 15, 2020, 1:47pm UTC](https://discourse.slicer.org/t/plastimatch-and-python-interactor/11556 "2020-05-15T13:47:25Z")\
**Posts on this page:** 8\
**Page:** 2

<div class="post-metadata">

**Author:** ![cpinter](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/cpinter/32/7995_2.png) [@cpinter](https://discourse.slicer.org/u/cpinter)\
**Post date:** [February 24, 2023, 3:51pm UTC](https://discourse.slicer.org/t/plastimatch-and-python-interactor/11556/21 "2023-02-24T15:51:03Z")

</div>

> [@Spiros\_Karkavitsas](#):
>
> since I have not searched it yet

Please do, and ask if something is not clear.

---

<div class="post-metadata">

**Author:** ![gcsharp](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/gcsharp/32/863_2.png) [@gcsharp](https://discourse.slicer.org/u/gcsharp)\
**Post date:** [February 24, 2023, 8:37pm UTC](https://discourse.slicer.org/t/plastimatch-and-python-interactor/11556/22 "2023-02-24T20:37:14Z")

</div>

Hi @Spiros_Karkavitsas. The terminology “mean Hausdorff” was created many years ago, before “mean surface distance” became the standard. Sorry for the confusion.

---

<div class="post-metadata">

**Author:** ![Spiros\_Karkavitsas](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/spiros_karkavitsas/32/18224_2.png) [@Spiros\_Karkavitsas](https://discourse.slicer.org/u/Spiros_Karkavitsas)\
**Post date:** [February 24, 2023, 9:05pm UTC](https://discourse.slicer.org/t/plastimatch-and-python-interactor/11556/23 "2023-02-24T21:05:37Z")

</div>

Hey and thanks for the clarification ☺

Actually,I did searched it and mean surface distance and mean Hausdorff distance seems to be indentical. Am I correct or not ?

Στις Παρ, 24 Φεβ 2023, 21:37 ο χρήστης Greg Sharp via 3D Slicer Community \<[notifications@slicer.discoursemail.com](mailto:notifications@slicer.discoursemail.com)\> έγραψε:

---

<div class="post-metadata">

**Author:** ![gcsharp](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/gcsharp/32/863_2.png) [@gcsharp](https://discourse.slicer.org/u/gcsharp)\
**Post date:** [February 24, 2023, 9:50pm UTC](https://discourse.slicer.org/t/plastimatch-and-python-interactor/11556/24 "2023-02-24T21:50:11Z")

</div>

There are literally (no kidding) more than 30 definitions of “mean surface distance”. You need to look at the mathematical definition.

Let me see if I can find it, there was a recent article which did a good job summarizing the current state. The basic idea is that comparing your result to literature is a mess. But any of them can be used as a relative comparison.

---

<div class="post-metadata">

**Author:** ![gcsharp](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/gcsharp/32/863_2.png) [@gcsharp](https://discourse.slicer.org/u/gcsharp)\
**Post date:** [February 24, 2023, 10:10pm UTC](https://discourse.slicer.org/t/plastimatch-and-python-interactor/11556/25 "2023-02-24T22:10:40Z")

</div>

Check out Vrtovec 2020 and Sherer 2021. You may take a look at my AAPM 2022 slides as well.

> **[2022-aapm.pdf](https://www.dropbox.com/s/f3qwpjgpw1pzkyh/2022-aapm.pdf)**

---

<div class="post-metadata">

**Author:** ![Spiros\_Karkavitsas](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/spiros_karkavitsas/32/18224_2.png) [@Spiros\_Karkavitsas](https://discourse.slicer.org/u/Spiros_Karkavitsas)\
**Post date:** [July 11, 2023, 7:23pm UTC](https://discourse.slicer.org/t/plastimatch-and-python-interactor/11556/26 "2023-07-11T19:23:28Z")

</div>

Hello again after a long time 🙂

Finally I will use this tool to compare the fat segmentation between groundtruth volumes and predicted volumes.

When I say volume, I mean 25 axial MR Slices. The voxel size is 1.95 by 1.95 by 10 in mm.

I would like to ask if the segment comparison module, does the Similarity metric calculation voxel wise.

Thank you for your time reading this message and hope for an answer

---

<div class="post-metadata">

**Author:** ![gcsharp](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/gcsharp/32/863_2.png) [@gcsharp](https://discourse.slicer.org/u/gcsharp)\
**Post date:** [July 11, 2023, 7:35pm UTC](https://discourse.slicer.org/t/plastimatch-and-python-interactor/11556/27 "2023-07-11T19:35:32Z")

</div>

Yes, it is voxelwise. If the images are different size, both are padded. If they are different voxel pitch, the compare image is resampled to the voxel pitch of the reference image.

---

<div class="post-metadata">

**Author:** ![Spiros\_Karkavitsas](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/spiros_karkavitsas/32/18224_2.png) [@Spiros\_Karkavitsas](https://discourse.slicer.org/u/Spiros_Karkavitsas)\
**Post date:** [July 11, 2023, 7:41pm UTC](https://discourse.slicer.org/t/plastimatch-and-python-interactor/11556/28 "2023-07-11T19:41:42Z")

</div>

Good, thank you for the immediate answer 🙂

[Previous page](https://discourse.slicer.org/t/plastimatch-and-python-interactor/11556.md?page=1)