Robust segmentation of infant brain MRI across multiple ages, modalities, and sites remains challenging due to the intrinsic heterogeneity caused by different MRI scanners, vendors, or acquisition sequences, as well as varying stages of neurodevelopment. To address this challenge, previous studies have explored domain adaptation (DA) algorithms from various perspectives, including feature alignment, entropy minimization, contrast synthesis (style transfer), and pseudo-labeling. This paper introduces a novel framework called MAPSeg (Masked Autoencoding and Pseudo-labelling Segmentation) to address the challenges of cross-age, cross-modality, and cross-site segmentation of subcortical regions in infant brain MRI. Utilizing 3D masked autoencoding as well as masked pseudo-labeling, the model is able to jointly learn from labeled source domain data and unlabeled target domain data. We evaluated our framework on expert-annotated datasets acquired from different ages and sites. MAPSeg consistently outperformed other methods, including previous state-of-the-art supervised baselines, domain generalization, and domain adaptation frameworks in segmenting subcortical regions regardless of age, modality, or acquisition site. The code and pretrained encoder will be publicly available at https://github.com/XuzheZ/MAPSeg

翻译：由于不同磁共振扫描仪、厂商或采集序列引起的固有异质性，以及神经发育的不同阶段，跨年龄、跨模态和跨站点的婴儿脑部磁共振成像鲁棒分割仍然面临挑战。为解决这一问题，以往研究从特征对齐、熵最小化、对比合成（风格迁移）及伪标签等多个角度探索了域自适应算法。本文提出一种名为MAPSeg（掩码自编码与伪标签分割）的新型框架，旨在解决婴儿脑部磁共振成像中丘脑等皮层下结构的跨年龄、跨模态及跨站点分割难题。该模型利用三维掩码自编码及掩码伪标签技术，能够联合学习标注源域数据与非标注目标域数据。我们在不同年龄和不同站点获取的专家标注数据集上评估了该框架。无论年龄、模态或采集站点如何，MAPSeg在分割皮层下结构方面均持续优于其他方法，包括先前的最先进监督基线、域泛化及域自适应框架。相关代码及预训练编码器将在https://github.com/XuzheZ/MAPSeg 公开发布。