Published January 5, 2023 | Version v1
Dataset Open

Retinal Fundus Multi-Disease Image Dataset (RFMiD) 2.0

Creators

  • 1. Center of Excellence in Signal and Image Processing, Shri Guru Gobind Singhji Institute of Engineering and Technology, Nanded, Maharashtra 431606, India
  • 2. The University of Texas Health Science Center at Houston
  • 3. Shri Ganapati Netralaya State of Art Eye Care Hospital, Jalna, Maharashtra, India
  • 4. Lions Eye Hospital, Nanded, Maharashtra, India
  • 5. Keya Eye Clinic, Pune, Maharashtra, India

Description

Retinal Fundus Multi-disease Image Dataset (RFMiD 2.0) is an auxiliary dataset to our previously published dataset. RFMiD 2.0 is a more challenging dataset to research society to develop the computer-based disease diagnosis system. Diabetic Retinopathy, cataracts, and refractive error in the eye are leading diseases that may lead to permanent vision loss more frequently. Therefore, developing an AI-based model to classify these diseases is useful for ophthalmologists. This dataset consists of 860 images of frequently and rarely observed 51 diseases. However, some images are labeled with multiple diseases. This dataset is useful for the research and development of AI-based medical healthcare systems in ophthalmology. 

Notes

RFMiD2.0 Dataset is classified into three sub-classes with disease distribution. The training set, validation set, and test set are three subfolders consisting of multi-labeled images. Each folder includes images and a .csv file containing labels. This distributed data can be utilized for the development of AI-based models.

Files

RFMiD2_0.zip

Files (63.7 MB)

Name Size Download all
md5:f9fe268dd74825fd89a9e212c1e48624
63.7 MB Preview Download