El Karania Diabetic Retinopathy Fundus Images from 20 Patients

39 real-clinic fundus images from 20 patients, graded 0–7 on the ETDRS scale. The dataset is sourced from Kaggle and contains clinical-grade retinal photographs. The author, organization, and specific collection details are unknown.

Use Cases

• Train image classification models based on ETDRS severity grades.
• Validate computer-aided diagnosis systems based on real-clinic fundus images.
• Benchmark model performance on a small, clinically sourced dataset.

Strengths

• 39 real-clinic fundus images provide authentic clinical data.
• Images are graded on the standardized ETDRS scale from 0 to 7.

Limitations

• The dataset is small with only 39 images, limiting statistical power.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Kaggle

Collection Method

Collection method unknown; described as real-clinic fundus images.