Abstract

Image-based artificial intelligence (AI) systems stand as the major modality for evaluating ophthalmic conditions. However, most of the currently available AI systems are designed for experimental research using single-central datasets. Most of them fell short of application in real-world clinical settings. In this study, we collected a dataset of 1,099 fundus images in both normal and pathologic eyes from 483 premature infants for intelligent retinopathy of prematurity (ROP) system development and validation. Dataset diversity was visualized with a spatial scatter plot. Image classification was conducted by three annotators. To the best of our knowledge, this is one of the largest fundus datasets on ROP, and we believe it is conducive to the real-world application of AI systems.

Details

Title
A fundus image dataset for intelligent retinopathy of prematurity system
Author
Zhao, Xinyu 1 ; Chen, Shaobin 2   VIAFID ORCID Logo  ; Zhang, Sifan 3 ; Liu, Yaling 1 ; Hu, Yarou 1 ; Yuan, Duo 1 ; Xie, Liqiong 4 ; Luo, Xiayuan 1 ; Zheng, Mianying 1 ; Tian, Ruyin 1 ; Chen, Yi 1 ; Tan, Tao 2 ; Yu, Zhen 1 ; Sun, Yue 2 ; Wu, Zhenquan 1 ; Zhang, Guoming 1 

1  Jinan University, Shenzhen Eye Institute, Shenzhen Eye Hospital, Shenzhen, China (GRID:grid.258164.c) (ISNI:0000 0004 1790 3548) 
2  Macao Polytechnic University, Macao Special Administrative Region of China, Faculty of Applied Sciences, Macao, China (GRID:grid.445017.3) (ISNI:0000 0004 1794 7946) 
3  New York University, Department of Biology, New York, US (GRID:grid.137628.9) (ISNI:0000 0004 1936 8753) 
4  Sun Yat-sen University, State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Guangzhou, China (GRID:grid.12981.33) (ISNI:0000 0001 2360 039X) 
Pages
543
Publication year
2024
Publication date
2024
Publisher
Nature Publishing Group
e-ISSN
20524463
Source type
Scholarly Journal
Language of publication
English
DOI
https://doi.org/10.1038/s41597-024-03362-5
ProQuest document ID
3060634981
Copyright
© The Author(s) 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.