There is a newer version of the record available.

Published March 8, 2026 | Version v1
Dataset Open

Annotated dataset for retinal fundus image segmentation; Vascular arcade and optic nerve

Authors/Creators

  • 1. ROR icon Universidad Autónoma de Baja California
  • 2. Universidad Autonoma de Baja California
  • 3. Universidad Autónoma de Baja California - Campus Ensenada

Description

This repository contains a set of manually generated segmentation masks derived from retinal fundus images from the public APTOS 2019 Blindness Detection dataset. The annotations correspond to two relevant anatomical structures in ophthalmology: the vascular arcade and the optic nerve. The dataset includes 500 masks in PNG format, along with annotation files in COCO (JSON) format and Python scripts used to generate the masks. This resource is intended to support the training and comparative evaluation of medical image segmentation models.

Files

annotations_COCO.json

Files (80.6 MB)

Name Size
md5:a2cf68a3538e7fcc10f69cd19a35c3ef
60.0 MB Preview Download
md5:da3f08a45b049a1140923d7e74473b06
1.7 kB Download
md5:9c96a1dc8dba91c0da2c8e49ec943e5b
20.4 MB Preview Download
md5:b46b5a475ce7013587ddc22c726475df
1.2 kB Preview Download
md5:7e0b215569cb3d7eb1ff677ea661418b
5.6 kB Download
md5:ad65d5c8f60acb972555763f42dcf4e3
225.0 kB Download

Additional details

Software

Development Status
Active