BioMedIA Group, Department of Computing, Imperial College London, 180 Queen's Gate, London, SW7 2AZ, UK; Division of Brain Sciences, Department of Medicine, Imperial College London, UK.
Division of Brain Sciences, Department of Medicine, Imperial College London, UK.
Med Image Anal. 2019 Dec;58:101539. doi: 10.1016/j.media.2019.101539. Epub 2019 Jul 26.
Machine learning, particularly deep learning has boosted medical image analysis over the past years. Training a good model based on deep learning requires large amount of labelled data. However, it is often difficult to obtain a sufficient number of labelled images for training. In many scenarios the dataset in question consists of more unlabelled images than labelled ones. Therefore, boosting the performance of machine learning models by using unlabelled as well as labelled data is an important but challenging problem. Self-supervised learning presents one possible solution to this problem. However, existing self-supervised learning strategies applicable to medical images cannot result in significant performance improvement. Therefore, they often lead to only marginal improvements. In this paper, we propose a novel self-supervised learning strategy based on context restoration in order to better exploit unlabelled images. The context restoration strategy has three major features: 1) it learns semantic image features; 2) these image features are useful for different types of subsequent image analysis tasks; and 3) its implementation is simple. We validate the context restoration strategy in three common problems in medical imaging: classification, localization, and segmentation. For classification, we apply and test it to scan plane detection in fetal 2D ultrasound images; to localise abdominal organs in CT images; and to segment brain tumours in multi-modal MR images. In all three cases, self-supervised learning based on context restoration learns useful semantic features and lead to improved machine learning models for the above tasks.
机器学习，尤其是深度学习，在过去几年中推动了医学图像分析的发展。基于深度学习训练一个好的模型需要大量的标记数据。然而，通常很难获得足够数量的标记图像进行训练。在许多情况下，所讨论的数据集包含的未标记图像比标记图像多。因此，通过使用未标记和标记数据来提高机器学习模型的性能是一个重要但具有挑战性的问题。自监督学习为解决这个问题提供了一种可能的解决方案。然而，现有的适用于医学图像的自监督学习策略并不能显著提高性能。因此，它们通常只能带来微不足道的改进。在本文中，我们提出了一种新的基于上下文恢复的自监督学习策略，以更好地利用未标记图像。上下文恢复策略具有三个主要特点：1）它学习语义图像特征；2）这些图像特征对不同类型的后续图像分析任务有用；3）其实现简单。我们在医学成像中的三个常见问题中验证了上下文恢复策略：分类、定位和分割。对于分类，我们将其应用于 2D 超声胎儿扫描平面检测、CT 图像中腹部器官定位和多模态 MR 图像中的脑肿瘤分割。在所有三种情况下，基于上下文恢复的自监督学习都可以学习到有用的语义特征，并为上述任务提供改进的机器学习模型。
