# NifTK/NiftyNet

[unmaintained] An open-source convolutional neural networks platform for research in medical image analysis and image-guided therapy

Repository: https://github.com/NifTK/NiftyNet
Canonical: https://ross.abutalabs.com/products/niftynet
Homepage: http://niftynet.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: tensorflow, distributed, ml, neural-network, python, python2, python3, pip, deep-neural-networks, deep-learning, convolutional-neural-networks, medical-imaging, medical-image-computing, medical-image-processing, medical-images, segmentation, gan, autoencoder, medical-image-analysis, image-guided-therapy
Archived: true
Last push: 2020-04-21T19:54:52+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3290, "days_push": 2325, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1374, forks 401 (observed 2026-08-28T04:04:32.941631+00:00)

## What it is
NiftyNet is a TensorFlow-based open-source convolutional neural networks platform for research in medical image analysis and image-guided therapy. It provides modular network components, pre-trained models, and support for 2D/2.5D/3D/4D medical imaging inputs, but is no longer maintained.

## Use cases
- segment 3D medical images like MRI and CT scans with deep learning
- train a 3D U-net or V-net on my own medical imaging dataset
- use pre-trained networks for medical image segmentation
- build GANs or autoencoders for medical image synthesis
- run multi-GPU training on volumetric medical images
- evaluate medical image segmentation with standard metrics

## When to choose
- you need a legacy TensorFlow 1.x platform for medical image segmentation research
- you want to reproduce results from papers that used NiftyNet
- you need pre-trained 3D medical imaging networks like HighRes3DNet or DeepMedic

## When to avoid
- you are starting a new project - use MONAI instead, which is its successor
- you need actively maintained software or modern TensorFlow/PyTorch support
- you need clinically validated software - NiftyNet is explicitly not for clinical use

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, machine-learning, image-processing, gpu-computing
- domain: deep-learning, machine-learning, healthcare, image-processing
- platform: python, windows
- tags: medical-imaging, segmentation, tensorflow, cnn, gan, autoencoder, unmaintained, image-guided-therapy, 3d-images, linux, macos, gpu

## Member repositories
- NifTK/NiftyNet (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:32.941631+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 2026-08-30T04:40:36.140515+00:00, confidence not recorded.
  - readme: https://github.com/NifTK/NiftyNet (fetched 2026-08-28T04:04:32.941631+00:00, sha ed80ad57474e)
- Data as of 2026-08-30T08:39:29.467469+00:00.