Testing the stability of a diabetic retinopathy classifier against image disturbances


In this post we show how a deep learning diabetic retinopathy classifier respond against disturbances in the input image. The classifier showed in the videos is a deep convolutional neural network of 16 layers with human expert performance in the classification of the disease into the 5 standarised classes.

In the next videos we make changes in the input image in order to study the robustness of the model. We study changes in rotation, hue, saturation and luminance.

Enjoy the videos. They are fun!

How the model respond to changes in Rotation

How the model respond to changes in Hue

How the model respond to changes in Saturation

How the model respond to changes in Luminance

Back to blog