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

RHONA ASGARI; JOSÉ IGNACIO ORLANDO; SEBASTIAN WALDSTEIN; FERDINAND SCHLANITZ; MAGDALENA BARATSITS; URSULA SCHMIDT-ERFURTH; HRVOJE BOGUNOVIC

Shenzhen

Conferencia; 22nd INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING & COMPUTER ASSISTED INTERVENTION; 2019

Shenzhen University

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 due to this surrogate task. We empirically validated our approach on a private and a 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.