# ellisdg/3DUnetCNN

Pytorch 3D U-Net Convolution Neural Network (CNN) designed for medical image segmentation

Repository: https://github.com/ellisdg/3DUnetCNN
Canonical: https://ross.abutalabs.com/products/3dunetcnn
Language: Python
License: MIT
License Family: permissive
Last push: 2025-11-06T17:31:15+00:00

## Health v2 (maintenance only)
Score: 45/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 50, release rhythm 8, longevity 100
- inputs: {"age_days": 3500, "days_push": 300, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2224, forks 666 (observed 2026-08-28T04:06:27.943848+00:00)

## What it is
A PyTorch library for building, training, and applying 3D U-Net convolutional neural networks for medical image segmentation. It provides configuration-driven training pipelines and tutorials based on MICCAI challenge datasets like BraTS.

## Use cases
- segment brain tumors from MRI scans
- train a 3D U-Net on volumetric medical images
- apply deep learning to medical imaging segmentation tasks
- reproduce MICCAI challenge segmentation results
- segment 3D anatomical structures in NIfTI volumes

## When to choose
- you need 3D (volumetric) image segmentation with U-Net architectures in PyTorch
- you are working with medical imaging data like MRI or CT scans
- you want a configuration-driven training setup with worked examples

## When to avoid
- you need 2D image segmentation only
- you want a general-purpose computer vision toolkit outside medical imaging
- you need a maintained GUI or clinical application rather than a research library

## Facets
- artifact type: library
- maturity: active
- function: deep-learning, machine-learning, image-processing, computer-vision
- domain: deep-learning, healthcare, machine-learning, image-processing
- platform: python, cross-platform
- tags: unet, medical-imaging, segmentation, pytorch, 3d-convolution, mri, brats

## Member repositories
- ellisdg/3DUnetCNN (main) score 45

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:27.943848+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 2026-08-30T02:44:58.358893+00:00, confidence not recorded.
  - readme: https://github.com/ellisdg/3DUnetCNN (fetched 2026-08-28T04:06:27.943848+00:00, sha 7a0e3c055962)
- Data as of 2026-08-30T08:39:29.467469+00:00.