A fundus image dataset for intelligent retinopathy of prematurity system

Xinyu Zhao; Shaobin Chen; Sifan Zhang; Yaling Liu; Yarou Hu; Duo Yuan; Liqiong Xie; Xiayuan Luo; Mianying Zheng; Ruyin Tian; Yi Chen; Tao Tan; Zhen Yu; Yue Sun; Zhenquan Wu; Guoming Zhang

doi:10.1038/s41597-024-03362-5

A fundus image dataset for intelligent retinopathy of prematurity system

Xinyu Zhao, Shaobin Chen, Sifan Zhang, Yaling Liu, Yarou Hu, Duo Yuan, Liqiong Xie, Xiayuan Luo, Mianying Zheng, Ruyin Tian, Yi Chen, Tao Tan, Zhen Yu, Yue Sun, Zhenquan Wu, Guoming Zhang

Faculty of Applied Sciences

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

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.

Original language	English
Article number	543
Journal	Scientific data
Volume	11
Issue number	1
DOIs	https://doi.org/10.1038/s41597-024-03362-5
Publication status	Published - Dec 2024

Access to Document

10.1038/s41597-024-03362-5

Cite this

@article{bbcbdd630c9e4ddbb839cf344133840a,

title = "A fundus image dataset for intelligent retinopathy of prematurity system",

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.",

author = "Xinyu Zhao and Shaobin Chen and Sifan Zhang and Yaling Liu and Yarou Hu and Duo Yuan and Liqiong Xie and Xiayuan Luo and Mianying Zheng and Ruyin Tian and Yi Chen and Tao Tan and Zhen Yu and Yue Sun and Zhenquan Wu and Guoming Zhang",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2024.",

year = "2024",

month = dec,

doi = "10.1038/s41597-024-03362-5",

language = "English",

volume = "11",

journal = "Scientific data",

issn = "2052-4463",

publisher = "Nature Publishing Group",

number = "1",

}

TY - JOUR

T1 - A fundus image dataset for intelligent retinopathy of prematurity system

AU - Zhao, Xinyu

AU - Chen, Shaobin

AU - Zhang, Sifan

AU - Liu, Yaling

AU - Hu, Yarou

AU - Yuan, Duo

AU - Xie, Liqiong

AU - Luo, Xiayuan

AU - Zheng, Mianying

AU - Tian, Ruyin

AU - Chen, Yi

AU - Tan, Tao

AU - Yu, Zhen

AU - Sun, Yue

AU - Wu, Zhenquan

AU - Zhang, Guoming

PY - 2024/12

Y1 - 2024/12

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85194523477&partnerID=8YFLogxK

U2 - 10.1038/s41597-024-03362-5

DO - 10.1038/s41597-024-03362-5

M3 - Article

C2 - 38802420

AN - SCOPUS:85194523477

SN - 2052-4463

VL - 11

JO - Scientific data

JF - Scientific data

IS - 1

M1 - 543

ER -

A fundus image dataset for intelligent retinopathy of prematurity system

Abstract

Access to Document

Other files and links

Fingerprint

Cite this