Welcome to the Indian Diabetic Retinopathy Image Dataset (IDRiD) website. On April 4th, 2018 we organized the "Diabetic Retinopathy: Segmentation and Grading Challenge" workshop at IEEE International Symposium on Biomedical Imaging (ISBI-2018), Omni Shoreham Hotel, Washington (D.C.), More information about the workshop can be found here.
Though the competition is now completed, the dataset has been made publicly available for research purposes through the IEEE Dataport repository. Link to access dataset: https://ieee-dataport.org/open-access/indian-diabetic-retinopathy-image-dataset-idridData Descriptor: http://www.mdpi.com/2306-5729/3/3/25
First Results and Analysis: https://doi.org/10.1016/j.media.2019.101561

Aim¶

The aim of this challenge is to evaluate algorithms for automated detection and grading of diabetic retinopathy and diabetic macular edema using retinal fundus images.

Abstract¶

Diabetic Retinopathy is the most prevalent cause of avoidable vision impairment, mainly affecting the working-age population in the world. Recent research has given a better understanding of requirements in clinical eye care practice to identify better and cheaper ways of identification, management, diagnosis and treatment of retinal disease. The importance of diabetic retinopathy screening programs and difficulty in achieving reliable early diagnosis of diabetic retinopathy at a reasonable cost needs attention to develop a computer-aided diagnosis tool. Computer-aided disease diagnosis in retinal image analysis could ease mass screening of the population with diabetes mellitus and help clinicians in utilizing their time more efficiently. The recent technological advances in computing power, communication systems, and machine learning techniques provide opportunities for biomedical engineers and computer scientists to meet the requirements of clinical practice. Diverse and representative retinal image sets are essential for developing and testing digital screening programs and the automated algorithms at their core. To the best of our knowledge, the database for this challenge, IDRiD (Indian Diabetic Retinopathy Image Dataset), is the first database representative of an Indian population. Moreover, it is the only dataset constituting typical diabetic retinopathy lesions and normal retinal structures annotated at a pixel level. This dataset provides information on the disease severity of diabetic retinopathy, and diabetic macular edema for each image. This makes it perfect for the development and evaluation of image analysis algorithms for early detection of diabetic retinopathy. 

About - Challenge¶

The challenge is subdivided into three tasks as follows (participants can submit results for at least one of the challenges):

• Lesion Segmentation: Segmentation of retinal lesions associated with diabetic retinopathy as microaneurysms, hemorrhages, hard exudates, and soft exudates. For more details please refer to Sub-challenge 1.
• Disease Grading: Classification of fundus images according to the severity level of diabetic retinopathy and diabetic macular edema. For more details please refer to Sub-challenge 2.
• Optic Disc and Fovea Detection: Automatic localization of optic disc and fovea center coordinates and also segmentation of optic disc. For more details please refer to Sub-challenge 3.

This Challenge is organized in conjunction with the 2018 IEEE International Symposium on Biomedical Imaging  (ISBI-2018).

Important Dates¶

Note: For Sub - Challenge 1: Participants have to submit results on the training and testing set along with the paper before the mentioned deadline. For Sub - Challenge 2 and 3: Participants have to submit results on the training set along with the short paper before the mentioned deadline.