We propose a novel teacher-student model for semi-supervised multi-organ segmentation. In teacher-student model, data augmentation is usually adopted on unlabeled data to regularize the consistent training between teacher and student. We start from a key perspective that fixed relative locations and variable sizes of different organs can provide distribution information where a multi-organ CT scan is drawn. Thus, we treat the prior anatomy as a strong tool to guide the data augmentation and reduce the mismatch between labeled and unlabeled images for semi-supervised learning. More specifically, we propose a data augmentation strategy based on partition-and-recovery N$^3$ cubes cross- and within- labeled and unlabeled images. Our strategy encourages unlabeled images to learn organ semantics in relative locations from the labeled images (cross-branch) and enhances the learning ability for small organs (within-branch). For within-branch, we further propose to refine the quality of pseudo labels by blending the learned representations from small cubes to incorporate local attributes. Our method is termed as MagicNet, since it treats the CT volume as a magic-cube and N$^3$-cube partition-and-recovery process matches with the rule of playing a magic-cube. Extensive experiments on two public CT multi-organ datasets demonstrate the effectiveness of MagicNet, and noticeably outperforms state-of-the-art semi-supervised medical image segmentation approaches, with +7% DSC improvement on MACT dataset with 10% labeled images. Code is available at https://github.com/DeepMed-Lab-ECNU/MagicNet.

翻译：我们提出了一种新型师生模型用于半监督多器官分割。在师生模型中，通常对未标注数据采用数据增强以约束师生网络间的一致性训练。本文从一个关键视角出发：不同器官固定的相对位置和可变的尺寸可提供多器官CT扫描的分布信息。因此，我们将先验解剖结构作为引导数据增强的强有力工具，从而减少半监督学习中标注与未标注图像之间的不匹配。具体而言，我们提出了一种基于跨标注/未标注图像的N$^3$立方体分割-恢复策略的数据增强方法。该策略既促使未标注图像从标注图像学习各器官在相对位置上的语义信息（跨分支），又通过增强小器官的学习能力（内部分支）提升模型性能。在内部分支中，我们进一步提出通过融合小立方体学习到的局部特征表示来优化伪标签质量。由于将CT体素数据视为魔方且N$^3$立方体的分割-恢复过程符合魔方游戏规则，该方法被命名为MagicNet。在两个公开CT多器官数据集上的大量实验证明了MagicNet的有效性，尤其在MACT数据集上仅使用10%标注图像即可获得较现有最优半监督医学图像分割方法提升7%的DSC指标。代码已开源至https://github.com/DeepMed-Lab-ECNU/MagicNet。