Scribble-based Domain Adaptation via Co-segmentation

TL;DR

This paper introduces a weakly-supervised domain adaptation method for medical image segmentation using scribbles, structured learning, and co-segmentation, achieving high performance with minimal annotations.

Contribution

It proposes a novel formulation combining structured learning and co-segmentation for domain adaptation using scribbles, simplifying training and reducing annotation effort.

Findings

Outperforms unsupervised methods in domain adaptation.

Achieves comparable results to fully-supervised approaches.

Validated on Vestibular Schwannoma segmentation from T1 to T2 scans.

Abstract

Although deep convolutional networks have reached state-of-the-art performance in many medical image segmentation tasks, they have typically demonstrated poor generalisation capability. To be able to generalise from one domain (e.g. one imaging modality) to another, domain adaptation has to be performed. While supervised methods may lead to good performance, they require to fully annotate additional data which may not be an option in practice. In contrast, unsupervised methods don't need additional annotations but are usually unstable and hard to train. In this work, we propose a novel weakly-supervised method. Instead of requiring detailed but time-consuming annotations, scribbles on the target domain are used to perform domain adaptation. This paper introduces a new formulation of domain adaptation based on structured learning and co-segmentation. Our method is easy to train, thanks to the introduction of a regularised loss. The framework is validated on Vestibular Schwannoma segmentation (T1 to T2 scans). Our proposed method outperforms unsupervised approaches and achieves comparable performance to a fully-supervised approach.