DeepDRiD: Diabetic Retinopathy—Grading and Image Quality Estimation Challenge

Summary

We described a challenge named “Diabetic Retinopathy (DR)—Grading and Image Quality Estimation Challenge” in conjunction with ISBI 2020 to hold three sub-challenges and develop deep learning models for DR image assessment and grading. The scientific community responded positively to the challenge, with 34 submissions from 574 registrations. In the challenge, we provided the DeepDRiD dataset containing 2,000 regular DR images (500 patients) and 256 ultra-widefield images (128 patients), both having DR quality and grading annotations. We discussed details of the top 3 algorithms in each sub-challenges. The weighted kappa for DR grading ranged from 0.93 to 0.82, and the accuracy for image quality evaluation ranged from 0.70 to 0.65. The results showed that image quality assessment can be used as a further target for exploration. We also have released the DeepDRiD dataset on GitHub to help develop automatic systems and improve human judgment in DR screening and diagnosis.

Graphical abstract

Highlights

• •

  Provides the DeepDRiD dataset, performance evaluation, top methods and results

• •

  Presents deep learning approaches in DR image quality assessment and grading

• •

  Discusses the future work of DR automatic screening

The bigger picture

Diabetic retinopathy (DR) is the most common disease caused by diabetes. Challenges are held to address real-world issues encountered in the design of DR automated screening systems to advance the technology in this area. Thus, we described a challenge named "Diabetic Retinopathy (DR)—Grading and Image Quality Estimation Challenge" in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI 2020) for fundus image assessment and DR grading. The scientific community responded positively to the challenge. In the challenge, we provided a deep DR image dataset (DeepDRiD) containing regular DR images and ultra-widefield (UWF) DR images, both having image quality and DR grading diagnosis. We discussed details of the three best algorithms in each sub-challenges. The results by the top algorithms showed that image quality assessment can be used as a target for further exploration.

Abstract

In DeepDRiD challenge, organizers hold a real-world exploration in diabetic retinopathy (DR) auto-screening systems using regular fundus images from 500 participants and ultra-widefield fundus images from 128 participants. Among the 34 participating teams, we summarized the top 3 teams in the three sub-challenges involved in DR grading and image quality assessment. In addition to providing new insights into image quality assessment strategy, these models can enhance the judgment of healthcare workers in DR screening and bring precise screening results.