# AI-Powered Automatic Segmentation Assistant for 3D Slicer

**URL:** <https://discourse.slicer.org/t/ai-powered-automatic-segmentation-assistant-for-3d-slicer/47860>\
**Category:** Feature requests\
**Created:** [August 11, 2026, 2:03pm UTC](https://discourse.slicer.org/t/ai-powered-automatic-segmentation-assistant-for-3d-slicer/47860 "2026-08-11T14:03:04Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![AIOmarRehan](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/aiomarrehan/32/82708_2.png) [@AIOmarRehan](https://discourse.slicer.org/u/AIOmarRehan)\
**Post date:** [August 11, 2026, 2:03pm UTC](https://discourse.slicer.org/t/ai-powered-automatic-segmentation-assistant-for-3d-slicer/47860/1 "2026-08-11T14:03:04Z")

</div>

Hi everyone,

I’m interested in contributing to 3D Slicer by developing an **AI-Powered Automatic Segmentation Assistant**.

The idea is to provide a user-friendly workflow for applying modern AI segmentation models to medical images and automatically creating/editing Slicer segmentations.

I’m considering integration with existing approaches such as **MONAI, nnU-Net, and other medical segmentation models** , while making the design modular so additional models can be added later.

Before starting implementation, I’d appreciate feedback from the Slicer community on whether this would be useful, whether similar functionality already exists, and what architecture/workflow would be most appropriate for an upstream contribution.

I’m particularly interested in suggestions regarding integration with **Segment Editor** and existing Slicer AI/segmentation infrastructure.

---

<div class="post-metadata">

**Author:** ![pieper](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/pieper/32/8_2.png) [@pieper](https://discourse.slicer.org/u/pieper)\
**Post date:** [August 11, 2026, 3:08pm UTC](https://discourse.slicer.org/t/ai-powered-automatic-segmentation-assistant-for-3d-slicer/47860/2 "2026-08-11T15:08:02Z")

</div>

Have you tried [nnInteractive](https://github.com/MIC-DKFZ/nnInteractive)? It’s already quite usable, but I’m sure there are additional features that would be nice. It would be good if you could contribute to the ongoing project instead of starting something new.