Retinal Fundus Multi-disease Image Dataset (RFMiD)

Citation Author(s):
Samiksha
Pachade
Center of Excellence in Signal and Image Processing, Shri Guru Gobind Singhji Institute of Engineering and Technology, Nanded, India
Prasanna
Porwal
Center of Excellence in Signal and Image Processing, Shri Guru Gobind Singhji Institute of Engineering and Technology, Nanded, India
Dhanshree
Thulkar
Veermata Jijabai Technological Institute, Mumbai, India
Manesh
Kokare
Center of Excellence in Signal and Image Processing, Shri Guru Gobind Singhji Institute of Engineering and Technology, Nanded, India
Girish
Deshmukh
Eye Clinic, Sushrusha Hospital, Nanded 431601, India
Vivek
Sahasrabuddhe
Department of Ophthalmology, Shankarrao Chavan Government Medical College, Nanded 431606, India
Luca
Giancardo
Center for Precision Health, School of Biomedical Informatics, University of Texas Health Science Center at Houston (UTHealth), Houston, USA
Gwenolé
Quellec
Inserm, UMR 1101, Brest, F-29200, France
Fabrice
Mériaudeau
ImViA EA 7535 and ERL VIBOT 6000, Université de Bourgogne, France
Submitted by:
Samiksha Pachade
Last updated:
Fri, 06/11/2021 - 15:16
DOI:
10.21227/s3g7-st65
Data Format:
Links:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

The world faces difficulties in terms of eye care, including treatment, quality of prevention, vision rehabilitation services, and scarcity of trained eye care experts. Early detection and diagnosis of ocular pathologies would enable forestall of visual impairment. One challenge that limits the adoption of computer-aided diagnosis tool by ophthalmologists is the number of sight-threatening rare pathologies, such as central retinal artery occlusion or anterior ischemic optic neuropathy, and others are usually ignored. In the past two decades, many publicly available datasets of color fundus images have been collected with a primary focus on diabetic retinopathy, glaucoma, age-related macular degeneration and few other frequent pathologies. To enable development of methods for automatic ocular disease classification of frequent diseases along with the rare pathologies, we have created a new Retinal Fundus Multi-disease Image Dataset (RFMiD). It consists of 3200 fundus images captured using three different fundus cameras with 46 conditions annotated through adjudicated consensus of two senior retinal experts. To the best of our knowledge, our dataset, RFMiD, is the only publicly available dataset that constitutes such a wide variety of diseases that appear in routine clinical settings. This dataset will enable the development of generalizable models for retinal screening.

Instructions: 

The dataset is divided into two parts:

A. RFMiD_All_Classes_Dataset: It consists of

1. Original color fundus images (3200 images divided into a training set (1920 images), validation (640 images), and testing set (640 images) - PNG Files)

2.  Groundtruth Labels for normal and abnormal (comprising of 45 different types of diseases/pathologies) categories (Divided into training, validation, and testing set - CSV Files)

 

B. RFMiD_Challenge_Dataset: It consists of

1. Original color fundus images (3200 images divided into a training set (1920 images), validation (640 images), and testing set (640 images) - PNG Files)

2. Groundtruth Labels for 28* different categories (Divided into training, validation, and testing set - CSV Files)

 

* The diseases having more than 10 images belong to an independent class and all other disease categories are merged and labeled as “OTHER”. This finally constitutes 28 classes for disease classification.

 

Detailed instructions about this dataset are available on the challenge website: https://riadd.grand-challenge.org/.

Comments

how i get this dataset because i am not having credit card

Submitted by Akanksha Bali on Fri, 01/15/2021 - 22:58

Is there any current competion on eye disease Prediction available. How to join. Please twll i am new on this

Submitted by Akanksha Bali on Fri, 01/15/2021 - 23:02

How to access this dataset, On clicking "Access On AWS" its giving an empty popup without any S3 URI

Submitted by SREENATH SUKUMAR on Tue, 01/26/2021 - 02:38

While accessing this dataset, it is showing an Empty popup without URI

Submitted by Sudheer Kumar on Wed, 02/17/2021 - 16:00

Ground Truths are unavailable.

Submitted by Arun Govindaiah on Mon, 11/15/2021 - 17:41