IDRiD: Diabetic Retinopathy – Segmentation and Grading Challenge

Prasanna Porwal, Samiksha Pachade, Manesh Kokare, Girish Deshmukh, Jaemin Son, Woong Bae, Lihong Liu, Jianzong Wang, Xinhui Liu, Liangxin Gao, Tian Bo Wu, Jing Xiao, Fengyan Wang, Baocai Yin, Yunzhi Wang, Gopichandh Danala, Linsheng He, Yoon Ho Choi, Yeong Chan Lee, Sang Hyuk JungZhongyu Li, Xiaodan Sui, Junyan Wu, Xiaolong Li, Ting Zhou, Janos Toth, Agnes Baran, Avinash Kori, Sai Saketh Chennamsetty, Mohammed Safwan, Varghese Alex, Xingzheng Lyu, Li Cheng, Qinhao Chu, Pengcheng Li, Xin Ji, Sanyuan Zhang, Yaxin Shen, Ling Dai, Oindrila Saha, Rachana Sathish, Tânia Melo, Teresa Araújo, Balazs Harangi, Bin Sheng, Ruogu Fang, Debdoot Sheet, Andras Hajdu, Yuanjie Zheng, Ana Maria Mendonça, Shaoting Zhang, Aurélio Campilho, Bin Zheng, Dinggang Shen, Luca Giancardo, Gwenolé Quellec, Fabrice Mériaudeau

Research output: Contribution to journalArticle

Abstract

Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is challenging due to the scarcity of medical professionals able to screen a growing global diabetic population at risk for DR. Computer-aided disease diagnosis in retinal image analysis could provide a sustainable approach for such large-scale screening effort. The recent scientific advances in computing capacity and machine learning approaches provide an avenue for biomedical scientists to reach this goal. Aiming to advance the state-of-the-art in automatic DR diagnosis, a grand challenge on “Diabetic Retinopathy – Segmentation and Grading” was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2018). In this paper, we report the set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD). There were three principal sub-challenges: lesion segmentation, disease severity grading, and localization of retinal landmarks and segmentation. These multiple tasks in this challenge allow to test the generalizability of algorithms, and this is what makes it different from existing ones. It received a positive response from the scientific community with 148 submissions from 495 registrations effectively entered in this challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top-performing participating solutions. The top-performing approaches utilized a blend of clinical information, data augmentation, and an ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.

Original languageEnglish
Article number101561
JournalMedical Image Analysis
Volume59
DOIs
Publication statusPublished - 2020 Jan
Externally publishedYes

Fingerprint

Diabetic Retinopathy
Screening
Image analysis
Learning systems
Imaging techniques
Datasets
Referral and Consultation
Population

Keywords

  • Challenge
  • Deep learning
  • Diabetic Retinopathy
  • Retinal image analysis

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

Porwal, P., Pachade, S., Kokare, M., Deshmukh, G., Son, J., Bae, W., ... Mériaudeau, F. (2020). IDRiD: Diabetic Retinopathy – Segmentation and Grading Challenge. Medical Image Analysis, 59, [101561]. https://doi.org/10.1016/j.media.2019.101561

IDRiD : Diabetic Retinopathy – Segmentation and Grading Challenge. / Porwal, Prasanna; Pachade, Samiksha; Kokare, Manesh; Deshmukh, Girish; Son, Jaemin; Bae, Woong; Liu, Lihong; Wang, Jianzong; Liu, Xinhui; Gao, Liangxin; Wu, Tian Bo; Xiao, Jing; Wang, Fengyan; Yin, Baocai; Wang, Yunzhi; Danala, Gopichandh; He, Linsheng; Choi, Yoon Ho; Lee, Yeong Chan; Jung, Sang Hyuk; Li, Zhongyu; Sui, Xiaodan; Wu, Junyan; Li, Xiaolong; Zhou, Ting; Toth, Janos; Baran, Agnes; Kori, Avinash; Chennamsetty, Sai Saketh; Safwan, Mohammed; Alex, Varghese; Lyu, Xingzheng; Cheng, Li; Chu, Qinhao; Li, Pengcheng; Ji, Xin; Zhang, Sanyuan; Shen, Yaxin; Dai, Ling; Saha, Oindrila; Sathish, Rachana; Melo, Tânia; Araújo, Teresa; Harangi, Balazs; Sheng, Bin; Fang, Ruogu; Sheet, Debdoot; Hajdu, Andras; Zheng, Yuanjie; Mendonça, Ana Maria; Zhang, Shaoting; Campilho, Aurélio; Zheng, Bin; Shen, Dinggang; Giancardo, Luca; Quellec, Gwenolé; Mériaudeau, Fabrice.

In: Medical Image Analysis, Vol. 59, 101561, 01.2020.

Research output: Contribution to journalArticle

Porwal, P, Pachade, S, Kokare, M, Deshmukh, G, Son, J, Bae, W, Liu, L, Wang, J, Liu, X, Gao, L, Wu, TB, Xiao, J, Wang, F, Yin, B, Wang, Y, Danala, G, He, L, Choi, YH, Lee, YC, Jung, SH, Li, Z, Sui, X, Wu, J, Li, X, Zhou, T, Toth, J, Baran, A, Kori, A, Chennamsetty, SS, Safwan, M, Alex, V, Lyu, X, Cheng, L, Chu, Q, Li, P, Ji, X, Zhang, S, Shen, Y, Dai, L, Saha, O, Sathish, R, Melo, T, Araújo, T, Harangi, B, Sheng, B, Fang, R, Sheet, D, Hajdu, A, Zheng, Y, Mendonça, AM, Zhang, S, Campilho, A, Zheng, B, Shen, D, Giancardo, L, Quellec, G & Mériaudeau, F 2020, 'IDRiD: Diabetic Retinopathy – Segmentation and Grading Challenge', Medical Image Analysis, vol. 59, 101561. https://doi.org/10.1016/j.media.2019.101561
Porwal P, Pachade S, Kokare M, Deshmukh G, Son J, Bae W et al. IDRiD: Diabetic Retinopathy – Segmentation and Grading Challenge. Medical Image Analysis. 2020 Jan;59. 101561. https://doi.org/10.1016/j.media.2019.101561
Porwal, Prasanna ; Pachade, Samiksha ; Kokare, Manesh ; Deshmukh, Girish ; Son, Jaemin ; Bae, Woong ; Liu, Lihong ; Wang, Jianzong ; Liu, Xinhui ; Gao, Liangxin ; Wu, Tian Bo ; Xiao, Jing ; Wang, Fengyan ; Yin, Baocai ; Wang, Yunzhi ; Danala, Gopichandh ; He, Linsheng ; Choi, Yoon Ho ; Lee, Yeong Chan ; Jung, Sang Hyuk ; Li, Zhongyu ; Sui, Xiaodan ; Wu, Junyan ; Li, Xiaolong ; Zhou, Ting ; Toth, Janos ; Baran, Agnes ; Kori, Avinash ; Chennamsetty, Sai Saketh ; Safwan, Mohammed ; Alex, Varghese ; Lyu, Xingzheng ; Cheng, Li ; Chu, Qinhao ; Li, Pengcheng ; Ji, Xin ; Zhang, Sanyuan ; Shen, Yaxin ; Dai, Ling ; Saha, Oindrila ; Sathish, Rachana ; Melo, Tânia ; Araújo, Teresa ; Harangi, Balazs ; Sheng, Bin ; Fang, Ruogu ; Sheet, Debdoot ; Hajdu, Andras ; Zheng, Yuanjie ; Mendonça, Ana Maria ; Zhang, Shaoting ; Campilho, Aurélio ; Zheng, Bin ; Shen, Dinggang ; Giancardo, Luca ; Quellec, Gwenolé ; Mériaudeau, Fabrice. / IDRiD : Diabetic Retinopathy – Segmentation and Grading Challenge. In: Medical Image Analysis. 2020 ; Vol. 59.
@article{9ee145c8fcc54d0ebca2eb5d17c9d6db,
title = "IDRiD: Diabetic Retinopathy – Segmentation and Grading Challenge",
abstract = "Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is challenging due to the scarcity of medical professionals able to screen a growing global diabetic population at risk for DR. Computer-aided disease diagnosis in retinal image analysis could provide a sustainable approach for such large-scale screening effort. The recent scientific advances in computing capacity and machine learning approaches provide an avenue for biomedical scientists to reach this goal. Aiming to advance the state-of-the-art in automatic DR diagnosis, a grand challenge on “Diabetic Retinopathy – Segmentation and Grading” was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2018). In this paper, we report the set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD). There were three principal sub-challenges: lesion segmentation, disease severity grading, and localization of retinal landmarks and segmentation. These multiple tasks in this challenge allow to test the generalizability of algorithms, and this is what makes it different from existing ones. It received a positive response from the scientific community with 148 submissions from 495 registrations effectively entered in this challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top-performing participating solutions. The top-performing approaches utilized a blend of clinical information, data augmentation, and an ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.",
keywords = "Challenge, Deep learning, Diabetic Retinopathy, Retinal image analysis",
author = "Prasanna Porwal and Samiksha Pachade and Manesh Kokare and Girish Deshmukh and Jaemin Son and Woong Bae and Lihong Liu and Jianzong Wang and Xinhui Liu and Liangxin Gao and Wu, {Tian Bo} and Jing Xiao and Fengyan Wang and Baocai Yin and Yunzhi Wang and Gopichandh Danala and Linsheng He and Choi, {Yoon Ho} and Lee, {Yeong Chan} and Jung, {Sang Hyuk} and Zhongyu Li and Xiaodan Sui and Junyan Wu and Xiaolong Li and Ting Zhou and Janos Toth and Agnes Baran and Avinash Kori and Chennamsetty, {Sai Saketh} and Mohammed Safwan and Varghese Alex and Xingzheng Lyu and Li Cheng and Qinhao Chu and Pengcheng Li and Xin Ji and Sanyuan Zhang and Yaxin Shen and Ling Dai and Oindrila Saha and Rachana Sathish and T{\^a}nia Melo and Teresa Ara{\'u}jo and Balazs Harangi and Bin Sheng and Ruogu Fang and Debdoot Sheet and Andras Hajdu and Yuanjie Zheng and Mendon{\cc}a, {Ana Maria} and Shaoting Zhang and Aur{\'e}lio Campilho and Bin Zheng and Dinggang Shen and Luca Giancardo and Gwenol{\'e} Quellec and Fabrice M{\'e}riaudeau",
year = "2020",
month = "1",
doi = "10.1016/j.media.2019.101561",
language = "English",
volume = "59",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

TY - JOUR

T1 - IDRiD

T2 - Diabetic Retinopathy – Segmentation and Grading Challenge

AU - Porwal, Prasanna

AU - Pachade, Samiksha

AU - Kokare, Manesh

AU - Deshmukh, Girish

AU - Son, Jaemin

AU - Bae, Woong

AU - Liu, Lihong

AU - Wang, Jianzong

AU - Liu, Xinhui

AU - Gao, Liangxin

AU - Wu, Tian Bo

AU - Xiao, Jing

AU - Wang, Fengyan

AU - Yin, Baocai

AU - Wang, Yunzhi

AU - Danala, Gopichandh

AU - He, Linsheng

AU - Choi, Yoon Ho

AU - Lee, Yeong Chan

AU - Jung, Sang Hyuk

AU - Li, Zhongyu

AU - Sui, Xiaodan

AU - Wu, Junyan

AU - Li, Xiaolong

AU - Zhou, Ting

AU - Toth, Janos

AU - Baran, Agnes

AU - Kori, Avinash

AU - Chennamsetty, Sai Saketh

AU - Safwan, Mohammed

AU - Alex, Varghese

AU - Lyu, Xingzheng

AU - Cheng, Li

AU - Chu, Qinhao

AU - Li, Pengcheng

AU - Ji, Xin

AU - Zhang, Sanyuan

AU - Shen, Yaxin

AU - Dai, Ling

AU - Saha, Oindrila

AU - Sathish, Rachana

AU - Melo, Tânia

AU - Araújo, Teresa

AU - Harangi, Balazs

AU - Sheng, Bin

AU - Fang, Ruogu

AU - Sheet, Debdoot

AU - Hajdu, Andras

AU - Zheng, Yuanjie

AU - Mendonça, Ana Maria

AU - Zhang, Shaoting

AU - Campilho, Aurélio

AU - Zheng, Bin

AU - Shen, Dinggang

AU - Giancardo, Luca

AU - Quellec, Gwenolé

AU - Mériaudeau, Fabrice

PY - 2020/1

Y1 - 2020/1

N2 - Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is challenging due to the scarcity of medical professionals able to screen a growing global diabetic population at risk for DR. Computer-aided disease diagnosis in retinal image analysis could provide a sustainable approach for such large-scale screening effort. The recent scientific advances in computing capacity and machine learning approaches provide an avenue for biomedical scientists to reach this goal. Aiming to advance the state-of-the-art in automatic DR diagnosis, a grand challenge on “Diabetic Retinopathy – Segmentation and Grading” was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2018). In this paper, we report the set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD). There were three principal sub-challenges: lesion segmentation, disease severity grading, and localization of retinal landmarks and segmentation. These multiple tasks in this challenge allow to test the generalizability of algorithms, and this is what makes it different from existing ones. It received a positive response from the scientific community with 148 submissions from 495 registrations effectively entered in this challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top-performing participating solutions. The top-performing approaches utilized a blend of clinical information, data augmentation, and an ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.

AB - Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is challenging due to the scarcity of medical professionals able to screen a growing global diabetic population at risk for DR. Computer-aided disease diagnosis in retinal image analysis could provide a sustainable approach for such large-scale screening effort. The recent scientific advances in computing capacity and machine learning approaches provide an avenue for biomedical scientists to reach this goal. Aiming to advance the state-of-the-art in automatic DR diagnosis, a grand challenge on “Diabetic Retinopathy – Segmentation and Grading” was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2018). In this paper, we report the set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD). There were three principal sub-challenges: lesion segmentation, disease severity grading, and localization of retinal landmarks and segmentation. These multiple tasks in this challenge allow to test the generalizability of algorithms, and this is what makes it different from existing ones. It received a positive response from the scientific community with 148 submissions from 495 registrations effectively entered in this challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top-performing participating solutions. The top-performing approaches utilized a blend of clinical information, data augmentation, and an ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.

KW - Challenge

KW - Deep learning

KW - Diabetic Retinopathy

KW - Retinal image analysis

UR - http://www.scopus.com/inward/record.url?scp=85074152892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074152892&partnerID=8YFLogxK

U2 - 10.1016/j.media.2019.101561

DO - 10.1016/j.media.2019.101561

M3 - Article

C2 - 31671320

AN - SCOPUS:85074152892

VL - 59

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

M1 - 101561

ER -