Recent studies on contrastive learning have achieved remarkable performance solely by leveraging few labels in the context of medical image segmentation. Existing methods mainly focus on instance discrimination and invariant mapping. However, they face three common pitfalls: (1) tailness: medical image data usually follows an implicit long-tail class distribution. Blindly leveraging all pixels in training hence can lead to the data imbalance issues, and cause deteriorated performance; (2) consistency: it remains unclear whether a segmentation model has learned meaningful and yet consistent anatomical features due to the intra-class variations between different anatomical features; and (3) diversity: the intra-slice correlations within the entire dataset have received significantly less attention. This motivates us to seek a principled approach for strategically making use of the dataset itself to discover similar yet distinct samples from different anatomical views. In this paper, we introduce a novel semi-supervised 2D medical image segmentation framework termed Mine yOur owN Anatomy (MONA), and make three contributions. First, prior work argues that every pixel equally matters to the model training; we observe empirically that this alone is unlikely to define meaningful anatomical features, mainly due to lacking the supervision signal. We show two simple solutions towards learning invariances - through the use of stronger data augmentations and nearest neighbors. Second, we construct a set of objectives that encourage the model to be capable of decomposing medical images into a collection of anatomical features in an unsupervised manner. Lastly, we both empirically and theoretically, demonstrate the efficacy of our MONA on three benchmark datasets with different labeled settings, achieving new state-of-the-art under different labeled semi-supervised settings

翻译：近年来，对比学习研究仅利用少量标注便在医学图像分割领域取得了显著成效。现有方法主要聚焦于实例判别与不变映射，但普遍存在三个问题：（1）长尾性：医学图像数据通常呈现隐式的长尾类别分布，盲目利用所有像素进行训练会导致数据不均衡问题，进而造成性能恶化；（2）一致性：由于不同解剖特征间的类内差异，分割模型是否真正学习了有意义且一致的解剖特征尚不明确；（3）多样性：整个数据集内切片间的相关性尚未得到足够关注。这促使我们探索一种基于原理的方法，策略性地利用数据集本身从不同解剖视角发现相似但不同的样本。本文提出一种名为"Mine yOur owN Anatomy"（MONA）的新型半监督二维医学图像分割框架，包含三项贡献。首先，现有研究认为每个像素对模型训练同等重要，但我们通过实验发现，仅凭这一点很难定义有意义的解剖特征，主要原因是缺乏监督信号。我们展示了两种学习不变性的简单方案——通过使用更强的数据增强与最近邻方法。其次，我们构建了一组目标函数，鼓励模型以无监督方式将医学图像分解为解剖特征集合。最后，我们通过实证与理论分析，在三种不同标注设置的基准数据集上验证了MONA的有效性，在不同半监督标注设置下均达到了最新最优性能。