# NRRD vs NIFTI: which one to choose?

**URL:** <https://discourse.slicer.org/t/nrrd-vs-nifti-which-one-to-choose/7799>\
**Category:** Support\
**Tags:** nifti, nrrd\
**Created:** [July 29, 2019, 6:41pm UTC](https://discourse.slicer.org/t/nrrd-vs-nifti-which-one-to-choose/7799 "2019-07-29T18:41:21Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![Akshay\_Goel](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/akshay_goel/32/9041_2.png) [@Akshay\_Goel](https://discourse.slicer.org/u/Akshay_Goel)\
**Post date:** [December 2, 2020, 1:33am UTC](https://discourse.slicer.org/t/nrrd-vs-nifti-which-one-to-choose/7799/6 "2020-12-02T01:33:20Z")

</div>

Hello all,

I am a radiologist working on deep learning research and I’m curious on any perspectives on storing raw dicom data as a 3D NumPy volume? This would allow for the fast load times for downstream applications.

I have worked with NifTI and converting files into NumPy ended up slowing things down a lot.

---

_[View the full topic](https://discourse.slicer.org/t/nrrd-vs-nifti-which-one-to-choose/7799)._