Comparison of domain adaptation techniques for white matter hyperintensity segmentation in brain MR images

• Published in: Medical image analysis Vol. 74; p. 102215
• Main Authors: Sundaresan, Vaanathi, Zamboni, Giovanna, Dinsdale, Nicola K., Rothwell, Peter M., Griffanti, Ludovica, Jenkinson, Mark
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.12.2021; Elsevier BV; Elsevier
• Subjects: Adaptation; Algorithms; Brain - diagnostic imaging; Data acquisition; Datasets; Deep learning; Domain adaptation; Domains; Humans; Image processing; Image Processing, Computer-Assisted; Image segmentation; Learning; Magnetic Resonance Imaging; Neural networks; Neural Networks, Computer; Performance evaluation; Robustness; Scanners; Segmentation; Substantia alba; Training; Transfer learning; White Matter - diagnostic imaging; White matter hyperintensities; Deep learning; Domain adaptation; White matter hyperintensities; Segmentation
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2021.102215

•We explored various domain adaptation methods for robust WM lesion segmentation.•We used a triplanar U-net ensemble network (TrUE-Net) as our baseline model.•Transfer learning: fine-tuning from the coarsest encoder layer gave good results.•Semi-supervised domain adversarial training of NNs (DANN) performed the best.•Among unsupervised methods, DANN performed better than domain unlearning. [Display omitted] 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.