Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, UK; Oxford-Nottingham Centre for Doctoral Training in Biomedical Imaging, University of Oxford, UK; Oxford India Centre for Sustainable Development, Somerville College, University of Oxford, UK.
Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, UK; Centre for Prevention of Stroke and Dementia, Nuffield Department of Clinical Neurosciences, University of Oxford, UK; Dipartimento di Scienze Biomediche, Metaboliche e Neuroscienze, Università di Modena e Reggio Emilia, Italy.
Med Image Anal. 2021 Dec;74:102215. doi: 10.1016/j.media.2021.102215. Epub 2021 Aug 17.
Robust automated segmentation of white matter hyperintensities (WMHs) in different datasets (domains) is highly challenging due to differences in acquisition (scanner, sequence), population (WMH amount and location) and limited availability of manual segmentations to train supervised algorithms. In this work we explore various domain adaptation techniques such as transfer learning and domain adversarial learning methods, including domain adversarial neural networks and domain unlearning, to improve the generalisability of our recently proposed triplanar ensemble network, which is our baseline model. We used datasets with variations in intensity profile, lesion characteristics and acquired using different scanners. For the source domain, we considered a dataset consisting of data acquired from 3 different scanners, while the target domain consisted of 2 datasets. We evaluated the domain adaptation techniques on the target domain datasets, and additionally evaluated the performance on the source domain test dataset for the adversarial techniques. For transfer learning, we also studied various training options such as minimal number of unfrozen layers and subjects required for fine-tuning in the target domain. On comparing the performance of different techniques on the target dataset, domain adversarial training of neural network gave the best performance, making the technique promising for robust WMH segmentation.
由于采集（扫描仪、序列）、人群（WMH 数量和位置）的差异以及可用的手动分割来训练监督算法的限制，在不同数据集（领域）中稳健地自动分割脑白质高信号（WMHs）极具挑战性。在这项工作中，我们探索了各种域自适应技术，例如迁移学习和域对抗学习方法，包括域对抗神经网络和域遗忘，以提高我们最近提出的三平面集成网络的泛化能力，这是我们的基线模型。我们使用了具有强度分布、病变特征和不同扫描仪采集差异的数据集。对于源域，我们考虑了一个由来自 3 个不同扫描仪采集的数据组成的数据集，而目标域则由 2 个数据集组成。我们在目标域数据集上评估了域自适应技术，并在对抗技术的源域测试数据集上评估了性能。对于迁移学习，我们还研究了各种训练选项，例如在目标域中进行微调所需的最少冻结层和受试者数量。在比较不同技术在目标数据集上的性能时，神经网络的域对抗训练获得了最佳性能，这使得该技术在稳健的 WMH 分割方面很有前途。
