# Resizing segmentation area

**URL:** <https://discourse.slicer.org/t/resizing-segmentation-area/40134>\
**Category:** Support\
**Tags:** segmentation, python, 3d-model, segmentations, segment-editor\
**Created:** [November 11, 2024, 9:30pm UTC](https://discourse.slicer.org/t/resizing-segmentation-area/40134 "2024-11-11T21:30:12Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![mohammad\_jafari](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/mohammad_jafari/32/78499_2.png) [@mohammad\_jafari](https://discourse.slicer.org/u/mohammad_jafari)\
**Post date:** [November 11, 2024, 9:30pm UTC](https://discourse.slicer.org/t/resizing-segmentation-area/40134/1 "2024-11-11T21:30:12Z")

</div>

Hello everyone thanks for this great community, i recently labeled segmentations for a deep learning project via 3d slicer segment editor module ,the original size of the reference volume is 256x256x175 each slice has 256 H and 256 W .after labeling tumor structures and saving them , during training of my model i realized that the size of input images are consuming memory and i want to reduce the size of the image (i.e. from 256x256x175 to , my concern is some of high details about the labeled areas will be lost in python , what modules in 3d slicer can i use to achieve the best results ? thank you

---

<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:** [November 11, 2024, 9:33pm UTC](https://discourse.slicer.org/t/resizing-segmentation-area/40134/2 "2024-11-11T21:33:23Z")

</div>

You can adjust the segmentation geometry by following [these instructions](https://slicer.readthedocs.io/en/latest/user_guide/modules/segmenteditor.html#segmentation-is-not-accurate-enough), just specify larger spacing instead of smaller spacing.

Of course, if you make the resolution of the segmentation coarser then small details may be lost.

---

<div class="post-metadata">

**Author:** ![mohammad\_jafari](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/mohammad_jafari/32/78499_2.png) [@mohammad\_jafari](https://discourse.slicer.org/u/mohammad_jafari)\
**Post date:** [November 12, 2024, 6:26pm UTC](https://discourse.slicer.org/t/resizing-segmentation-area/40134/3 "2024-11-12T18:26:27Z")

</div>

Thank you for responding.