# wasserth/TotalSegmentator

Tool for robust segmentation of >100 important anatomical structures in CT and MR images

Repository: https://github.com/wasserth/TotalSegmentator
Canonical: https://ross.abutalabs.com/products/totalsegmentator
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-13T09:31:46+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 8, longevity 100
- inputs: {"age_days": 1687, "days_push": 20, "days_rel": 595, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2952, forks 473 (observed 2026-08-28T04:07:32.045948+00:00)

## What it is
TotalSegmentator is a Python command-line tool that robustly segments over 100 anatomical structures in CT and MR images using deep learning models built on nnUNet. It supports Nifti and DICOM inputs, runs on CPU or GPU, and offers subtasks, body statistics prediction, and a 3D Slicer extension.

## Use cases
- segment organs in CT scans
- segment anatomical structures in MRI images
- convert DICOM slices to segmentation masks
- estimate body stats like height and weight from CT
- run vertebrae segmentation on spine images
- batch process medical images for research

## When to choose
- you need automated multi-structure segmentation of CT or MR images
- you want a robust pretrained model that generalizes across scanners and protocols
- you need a CLI tool that works on CPU and GPU across Linux, Mac, and Windows

## When to avoid
- you need segmentation of structures not covered by its tasks
- you require real-time or interactive segmentation rather than batch inference
- you cannot install Python 3.10+ and PyTorch dependencies

## Facets
- artifact type: cli-tool
- maturity: active
- function: machine-learning, image-processing, computer-vision, cli
- domain: healthcare, machine-learning, image-processing
- platform: windows, python, cli
- tags: medical-imaging, segmentation, ct, mri, nifti, dicom, nnunet, anatomy, linux, macos, gpu

## Member repositories
- wasserth/TotalSegmentator (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:32.045948+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:32:39.114012+00:00, confidence not recorded.
  - readme: https://github.com/wasserth/TotalSegmentator (fetched 2026-08-28T04:07:32.045948+00:00, sha 23337496db97)
  - registry_pypi: https://pypi.org/pypi/totalsegmentator/json (fetched 2026-08-29T09:47:46.734075+00:00, sha 409b428dc867)
- Data as of 2026-08-30T08:39:29.467469+00:00.