Fast and lightweight MRSegmentator CLI powered by the KonfAI framework.
Project description
MRSegmentator-KonfAI
Fast and lightweight MRI segmentation built on the MRSegmentator model using the KonfAI framework
🧩 Overview
MRSegmentator-KonfAI is a lightweight command-line interface (CLI) for running MRSegmentator
models through the KonfAI deep learning framework.
It provides fast inference for MRI segmentation tasks, even on low-resource hardware.
Models are automatically downloaded from Hugging Face Hub.
🚀 Installation
From PyPI:
pip install mrsegmentator-konfai
From source:
git clone https://github.com/vboussot/MRSegmentator-KonfAI.git
cd MRSegmentator-KonfAI
pip install .
⚙️ Usage
Run inference on an MRI scan:
mrsegmentator-konfai -i path/to/input.nii.gz -o path/to/output_seg.nii.gz
Optional arguments
| Flag | Description | Default |
|---|---|---|
-i, --input |
Path to the input MRI volume | required |
-o, --output |
Path to save the segmentation | Seg.nii.gz |
-f, --folds |
Number of model folds to ensemble (1–5) | 2 |
-g, --gpu |
List of GPUs to use (e.g. 0, 0,1) |
CPU if unset |
--cpu |
Number of CPU cores to use (if no GPU) | 1 |
-quiet |
Suppress console output | off |
Example:
mrsegmentator-konfai -i subject01.nii.gz -o seg_subject01.nii.gz --gpu 0 -f 3
🧠 Features
- ⚡ Fast inference using KonfAI
- 🤗 Automatic model download from Hugging Face
- 🧩 Support for ensemble models (multi-fold prediction)
- 🧾 Multi-format compatibility: supports all major medical image formats handled by ITK
📖 Reference
This package is based on the original MRSegmentator by
Henrik Haentze et al., a deep-learning-based method for full body MRI segmentation.
For scientific use, please cite the original MRSegmentator work in addition to this CLI tool.
🧾 License
This repository is released under the Apache 2.0 License.
Original MRSegmentator license and copyright remain with their respective authors.
🔗 Links
- 🧠 Original MRSegmentator: github.com/hhaentze/MRSegmentator
- ⚙️ KonfAI Framework: github.com/vboussot/KonfAI
- 🤗 Model Hub: huggingface.co/VBoussot/MRSegmentator-KonfAI
- 📦 PyPI Package: pypi.org/project/mrsegmentator-konfai
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mrsegmentator_konfai-1.4.5.tar.gz.
File metadata
- Download URL: mrsegmentator_konfai-1.4.5.tar.gz
- Upload date:
- Size: 8.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
20bec78447c87fc33f7dba711ba307e15b5325ed24b71a219382cb4afcf4ec4e
|
|
| MD5 |
6352bd90a34db0cb1263c38a5342fd4d
|
|
| BLAKE2b-256 |
cb199d2ac49a94bfaaa4bf9bf0b354c1a57f9f6f1262310d880df73640ee308c
|
Provenance
The following attestation bundles were made for mrsegmentator_konfai-1.4.5.tar.gz:
Publisher:
publish.yml on vboussot/KonfAI
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
mrsegmentator_konfai-1.4.5.tar.gz -
Subject digest:
20bec78447c87fc33f7dba711ba307e15b5325ed24b71a219382cb4afcf4ec4e - Sigstore transparency entry: 785146024
- Sigstore integration time:
-
Permalink:
vboussot/KonfAI@6c5762ac1f22d7abee44f2a6f48241bc15d1863a -
Branch / Tag:
refs/tags/v1.4.5 - Owner: https://github.com/vboussot
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@6c5762ac1f22d7abee44f2a6f48241bc15d1863a -
Trigger Event:
push
-
Statement type:
File details
Details for the file mrsegmentator_konfai-1.4.5-py3-none-any.whl.
File metadata
- Download URL: mrsegmentator_konfai-1.4.5-py3-none-any.whl
- Upload date:
- Size: 11.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f38d3917f096586a6b2870f6ffd5a6821fbacaa5c8c1f4c6b803b0638323e19f
|
|
| MD5 |
56759acc40a395ad5d31acf0c901c269
|
|
| BLAKE2b-256 |
bda6d38c6080f772d6278df85925b6bf379861693296fc4dd65ba1592af67be3
|
Provenance
The following attestation bundles were made for mrsegmentator_konfai-1.4.5-py3-none-any.whl:
Publisher:
publish.yml on vboussot/KonfAI
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
mrsegmentator_konfai-1.4.5-py3-none-any.whl -
Subject digest:
f38d3917f096586a6b2870f6ffd5a6821fbacaa5c8c1f4c6b803b0638323e19f - Sigstore transparency entry: 785146092
- Sigstore integration time:
-
Permalink:
vboussot/KonfAI@6c5762ac1f22d7abee44f2a6f48241bc15d1863a -
Branch / Tag:
refs/tags/v1.4.5 - Owner: https://github.com/vboussot
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@6c5762ac1f22d7abee44f2a6f48241bc15d1863a -
Trigger Event:
push
-
Statement type: