Skip to content

This is a Categorical Detection and Prediction Task based on subset of a Kaggle dataset from Eye Images (Aravind Eye hospital) - APTOS 2019 Challenge. The goal is to predict the Blindness Stage (0-4) class from the Eye retina Image using Deep Learning Models (transfer learning via resnet50). This Automated System would speed up Blindness detecti…

Notifications You must be signed in to change notification settings

akshitadixit/Retinopathy

Repository files navigation

Diabetic Retinopathy Detection

We first try to understand the problem we will be dealing with. The below image (credit: https://www.eyeops.com/) tells us the 5 very common symptoms of DR(diabetic retinopathy).

img

The Kaggle competition that introduced the dataset wrote:

You are provided with a large set of retina images taken using fundus photography under a variety of imaging conditions. A clinician has rated each image for the severity of diabetic retinopathy on a scale of 0 to 4:

0 - No DR

1 - Mild

2 - Moderate

3 - Severe

4 - Proliferative DR

Like any real-world data set, you will encounter noise in both the images and labels. Images may contain artifacts, be out of focus, underexposed, or overexposed. The images were gathered from multiple clinics using a variety of cameras over an extended period of time, which will introduce further variation.

Original Dataset samples:

image

Dataset after pre-processing:

image

About

This is a Categorical Detection and Prediction Task based on subset of a Kaggle dataset from Eye Images (Aravind Eye hospital) - APTOS 2019 Challenge. The goal is to predict the Blindness Stage (0-4) class from the Eye retina Image using Deep Learning Models (transfer learning via resnet50). This Automated System would speed up Blindness detecti…

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published