# Multiclass segmentation as multitask learning for drusen segmentation in retinal optical coherence tomography

## TL;DR

This paper introduces a multi-decoder multitask learning approach for improved drusen segmentation in retinal OCT scans, enhancing accuracy over traditional methods by modeling layer boundaries and drusen as related tasks.

## Contribution

The paper presents a novel multi-decoder architecture with class-specific branches and inter-branch connections for better drusen and layer segmentation in OCT images.

## Key findings

- Outperforms baseline models in layer and drusen segmentation
- Validated on private and public datasets with consistent improvements
- Effective in early and intermediate AMD cases

## Abstract

Automated drusen segmentation in retinal optical coherence tomography (OCT) scans is relevant for understanding age-related macular degeneration (AMD) risk and progression. This task is usually performed by segmenting the top/bottom anatomical interfaces that define drusen, the outer boundary of the retinal pigment epithelium (OBRPE) and the Bruch's membrane (BM), respectively. In this paper we propose a novel multi-decoder architecture that tackles drusen segmentation as a multitask problem. Instead of training a multiclass model for OBRPE/BM segmentation, we use one decoder per target class and an extra one aiming for the area between the layers. We also introduce connections between each class-specific branch and the additional decoder to increase the regularization effect of this surrogate task. We validated our approach on private/public data sets with 166 early/intermediate AMD Spectralis, and 200 AMD and control Bioptigen OCT volumes, respectively. Our method consistently outperformed several baselines in both layer and drusen segmentation evaluations.