# AMD Severity Prediction And Explainability Using Image Registration And Deep Embedded Clustering

## TL;DR

This paper introduces a deep learning approach combining image registration and clustering to predict and explain AMD severity from OCT images, achieving high accuracy and improved interpretability.

## Contribution

It presents a novel method integrating image registration and deep embedded clustering for AMD severity prediction with enhanced explainability.

## Key findings

- Achieves state-of-the-art classification performance
- Performs well on unseen data
- Provides better explainability than traditional methods

## Abstract

We propose a method to predict severity of age related macular degeneration (AMD) from input optical coherence tomography (OCT) images. Although there is no standard clinical severity scale for AMD, we leverage deep learning (DL) based image registration and clustering methods to identify diseased cases and predict their severity. Experiments demonstrate our approach's disease classification performance matches state of the art methods. The predicted disease severity performs well on previously unseen data. Registration output provides better explainability than class activation maps regarding label and severity decisions