Multiclass segmentation as multitask learning for drusen segmentation in retinal optical coherence tomography
This work addresses a domain-specific problem for medical imaging in ophthalmology, focusing on incremental improvements in segmentation accuracy.
The paper tackled automated drusen segmentation in retinal OCT scans for AMD risk assessment by proposing a multi-decoder architecture that treats it as a multitask problem, and the method consistently outperformed baselines on private and public datasets.
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.