# orobix/retina-unet

Retina blood vessel segmentation with a convolutional neural network

Repository: https://github.com/orobix/retina-unet
Canonical: https://ross.abutalabs.com/products/retina-unet
Language: Python
License Family: other
Last push: 2022-09-08T16:41:42+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3673, "days_push": 1455, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1354, forks 464 (observed 2026-08-28T04:04:29.066839+00:00)

## What it is
A Python implementation of a U-Net convolutional neural network for segmenting blood vessels in retina fundus images. It performs binary pixel-wise classification and achieves state-of-the-art AUC results on the DRIVE and STARE datasets.

## Use cases
- segment blood vessels in retina fundus images
- train a U-Net model for medical image segmentation
- reproduce state-of-the-art results on the DRIVE dataset
- apply deep learning to retinal vessel detection
- learn how to implement pixel-wise binary classification with CNNs

## When to choose
- you need a proven U-Net baseline for retinal vessel segmentation
- you want to benchmark against DRIVE/STARE dataset results
- you are studying medical image segmentation with CNNs

## When to avoid
- you need a maintained, production-ready medical imaging pipeline
- you require a permissive or clearly defined license
- you need segmentation of other anatomical structures without modification

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: deep-learning, computer-vision, image-processing, healthcare
- platform: python
- tags: u-net, medical-imaging, semantic-segmentation, retina, fundus-images, keras, drive-dataset, gpu

## Member repositories
- orobix/retina-unet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:29.066839+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 2026-08-30T04:42:03.530246+00:00, confidence not recorded.
  - readme: https://github.com/orobix/retina-unet (fetched 2026-08-28T04:04:29.066839+00:00, sha be172f786a7e)
- Data as of 2026-08-30T08:39:29.467469+00:00.