A Deep Learning Interpretable Classifier for Diabetic Retinopathy Disease Grading

TL;DR

This paper introduces an interpretable deep learning classifier for diabetic retinopathy that not only classifies disease severity from retinal images but also provides visual explanations to aid expert understanding.

Contribution

The paper presents a novel interpretable deep neural network model that assigns contribution scores to input features, enhancing transparency in diabetic retinopathy classification.

Findings

Achieved accurate classification of retinopathy severity levels.

Generated visual maps that aid expert interpretation.

Improved model transparency with linear contribution scoring.

Abstract

Deep neural network models have been proven to be very successful in image classification tasks, also for medical diagnosis, but their main concern is its lack of interpretability. They use to work as intuition machines with high statistical confidence but unable to give interpretable explanations about the reported results. The vast amount of parameters of these models make difficult to infer a rationale interpretation from them. In this paper we present a diabetic retinopathy interpretable classifier able to classify retine images into the different levels of disease severity and of explaining its results by assigning a score for every point in the hidden and input space, evaluating its contribution to the final classification in a linear way. The generated visual maps can be interpreted by an expert in order to compare its own knowledge with the interpretation given by the model.