> ## Documentation Index
> Fetch the complete documentation index at: https://docs.spine.altician.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Segmentation Overview

> AI-powered automatic spine segmentation for research use

## How It Works

The AI model automatically segments spine structures from T2-weighted MRI scans. It segments:

* **Vertebrae** — C1 through S1 (cervical, thoracic, lumbar, sacral)
* **Intervertebral Discs** — C2/3 through L5/S1
* **Spinal Canal** — The central canal containing the spinal cord

<img src="https://mintcdn.com/altician/0YBh5K6l-27QqsAD/images/mesh-3d.png?fit=max&auto=format&n=0YBh5K6l-27QqsAD&q=85&s=5724d3b0756edad9c57b113b105135f3" alt="3D segmentation result" width="1920" height="1080" data-path="images/mesh-3d.png" />

## How It Works

The model uses a two-phase approach based on nnU-Net:

1. **Semantic segmentation** — Classifies each voxel into tissue types (vertebra, disc, canal, background)
2. **Instance segmentation** — Separates individual vertebrae and discs (e.g., L1 vs L2)

The result is rendered as 3D meshes overlaid on the MRI volume.

## Requirements

* **Spine Helper** must be installed and running (see [Helper Setup](/segmentation/helper-setup))
* **T2-weighted MRI** is optimal (the model is trained on T2W data)

<Note>
  Segmentation is optimized for T2-weighted sagittal spine MRI. Results on other contrasts may vary.
</Note>