/Diabetic-Retinopathy

Diabetic Retinopathy Detection is an ATPOS Kaggle competition.

Primary LanguagePython

Diabetic-Retinopathy

The problem statement is an open challenge problem in Kaggle Competition. This problem aims to develop a system which could help ophthalmologists to detect blindness before it happened. Millions of people suffer from diabetic retinopathy, the leading cause of blindness among working aged adults. In India, Aravind Eye Hospital hopes to detect and prevent this disease among people living in rural areas where medical screening is difficult to conduct. APTOS (Asia Pacific Tele-Ophthalmology Society Symposium) has provided eye fundus images under a variety of imaging conditions with labels to detect the DR level in retinal images of person.

Each image is rated on a scale of 0 to 4:

  • 0 – No DR
  • 1 – Mild
  • 2 – Moderate
  • 3 – Severe
  • 4 – Proliferative DR

Normal Eye v/s Diabetic Retinopathy eye

Normal Eye v/s Diabetic Retinopathy Eye

Visualizations of datasets

Visualizations of datasets

Output Predicted DR levels

Output