Deep learning models often need sufficient supervision (i.e. labelled data) in order to be trained effectively. By contrast, humans can swiftly learn to identify important anatomy in medical images like MRI and CT scans, with minimal guidance. This recognition capability easily generalises to new images from different medical facilities and to new tasks in different settings. This rapid and generalisable learning ability is largely due to the compositional structure of image patterns in the human brain, which are not well represented in current medical models. In this paper, we study the utilisation of compositionality in learning more interpretable and generalisable representations for medical image segmentation. Overall, we propose that the underlying generative factors that are used to generate the medical images satisfy compositional equivariance property, where each factor is compositional (e.g. corresponds to the structures in human anatomy) and also equivariant to the task. Hence, a good representation that approximates well the ground truth factor has to be compositionally equivariant. By modelling the compositional representations with learnable von-Mises-Fisher (vMF) kernels, we explore how different design and learning biases can be used to enforce the representations to be more compositionally equivariant under un-, weakly-, and semi-supervised settings. Extensive results show that our methods achieve the best performance over several strong baselines on the task of semi-supervised domain-generalised medical image segmentation. Code will be made publicly available upon acceptance at https://github.com/vios-s.

翻译：深度学习模型通常需要足够的监督（即标注数据）才能有效训练。相比之下，人类可以借助极少的指导，迅速学会识别医学图像（如MRI和CT扫描）中的重要解剖结构。这种识别能力能够轻松泛化到来自不同医疗设备的新图像以及不同环境下的新任务。这种快速且可泛化的学习能力主要源于人脑中图像模式的组合结构，而当前医学模型并未很好地表征这一结构。本文研究了如何利用组合性来学习更具可解释性和泛化性的医学图像分割表示。总体而言，我们提出用于生成医学图像的潜在生成因子满足组合等变性，其中每个因子既具有组合性（例如与人体解剖结构对应），又对任务保持等变性。因此，能够良好近似真实因子的优秀表示必须具有组合等变性。通过使用可学习的冯·米塞斯-费舍尔（vMF）核来建模组合表示，我们探索了如何利用不同的设计和学习偏差，在无监督、弱监督和半监督设置下强制表示更具组合等变性。大量实验结果表明，在半监督域泛化医学图像分割任务中，我们的方法在多个强基线方法上取得了最佳性能。代码将在论文被接收后于https://github.com/vios-s公开。