# How to get image that requested scale from 3d slicer (save as NITFI)? 

**URL:** <https://discourse.slicer.org/t/how-to-get-image-that-requested-scale-from-3d-slicer-save-as-nitfi/16662>\
**Category:** Support\
**Tags:** segmentation, dicom, python\
**Created:** [March 20, 2021, 10:55pm UTC](https://discourse.slicer.org/t/how-to-get-image-that-requested-scale-from-3d-slicer-save-as-nitfi/16662 "2021-03-20T22:55:52Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![KAMONCHAT\_APIVANICHK](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/kamonchat_apivanichk/32/10368_2.png) [@KAMONCHAT\_APIVANICHK](https://discourse.slicer.org/u/KAMONCHAT_APIVANICHK)\
**Post date:** [March 20, 2021, 10:55pm UTC](https://discourse.slicer.org/t/how-to-get-image-that-requested-scale-from-3d-slicer-save-as-nitfi/16662/1 "2021-03-20T22:55:52Z")

</div>

I am researching about segmentation by deep learning via python then I would like to save CT Scan in .png or .jpg for using as input dataset but pictures what I got is bone-scale like the first picture. Have any way I can get picture like the second picture.

The first picture

 ![6_im000056](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/4/b/4bd60aa12a318ba8e8f5975eaad1ecd1c60468dc.jpeg)

The second picture

 ![Untitled](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/5/8/584f4eae442d8d74001512e4f68d82f3c083bd66.jpeg)

---

<div class="post-metadata">

**Author:** ![lassoan](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/lassoan/32/13_2.png) [@lassoan](https://discourse.slicer.org/u/lassoan)\
**Post date:** [March 25, 2021, 1:53pm UTC](https://discourse.slicer.org/t/how-to-get-image-that-requested-scale-from-3d-slicer-save-as-nitfi/16662/2 "2021-03-25T13:53:02Z")

</div>

> [@KAMONCHAT\_APIVANICHK](#):
>
> I would like to save CT Scan in .png or .jpg for using as input dataset

I would not recommend to export as png or jpg but instead use deep learning frameworks that are properly equipped to work with medical images (and can load commonly used medical image file formats), such as [monai](https://monai.io/).