Multi-Domain Adaptation in Brain MRI through Paired Consistency and Adversarial Learning
This work addresses the challenge of domain adaptation in medical imaging for brain MRI segmentation, which is incremental as it builds on existing semi-supervised learning and domain adaptation techniques.
The paper tackles the problem of supervised learning algorithms failing to generalize across different acquisition parameters in brain MRI by introducing a multi-domain adaptation method using consistency loss and adversarial learning. The method significantly outperforms other domain adaptation baselines on white matter lesion hyperintensity segmentation, with results shown on the MICCAI 2017 challenge data as the source domain and two target domains.
Supervised learning algorithms trained on medical images will often fail to generalize across changes in acquisition parameters. Recent work in domain adaptation addresses this challenge and successfully leverages labeled data in a source domain to perform well on an unlabeled target domain. Inspired by recent work in semi-supervised learning we introduce a novel method to adapt from one source domain to $n$ target domains (as long as there is paired data covering all domains). Our multi-domain adaptation method utilises a consistency loss combined with adversarial learning. We provide results on white matter lesion hyperintensity segmentation from brain MRIs using the MICCAI 2017 challenge data as the source domain and two target domains. The proposed method significantly outperforms other domain adaptation baselines.