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 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, our extensive results on three benchmark datasets with different labeled settings validate the effectiveness of our proposed MONA which achieves new state-of-the-art under different labeled settings.
翻译:最近关于对比性学习的研究仅通过在医学图像分割背景下利用少数标签取得了显著的成绩。现有方法主要侧重于实例歧视和差异性绘图。然而,它们面临三个常见的陷阱:(1)尾端:医学图像数据通常采用隐含长尾类分布。盲目地利用培训中的所有像素可能导致数据失衡问题,并导致性能恶化;(2)一致性:由于不同解剖特征之间不同的解剖特征之间的差异,一个分解模型是否学到了有意义和一致的解剖学特征,这一点仍然不清楚;(3)多样性:整个数据集内部的切片相关性受到的广泛关注要少得多。这促使我们寻求一种有原则的方法,从战略上利用数据集本身,从不同的解剖学观点中发现相似但又不同的样本。在本文中,我们引入了一个新的半监督性的医学图像分解框架(Mine 和OUR OMATIMA 模型(MOA) ), 做出三项贡献。首先,前的工作论证说,每个像素一样,对模型培训有同样的重要性;我们观察整个数据集的不精细的设置,我们无法从实验性结构上找到一个更精确的模型的模型,我们最精确的路径,我们无法在第二层次上找到一个更精确的解的模型的解的解析的解析的解的解的解的解的解析的解析的解析图图图。