论文标题
软CP：用于医学病变语义分割的可靠有效的数据增强
Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions
论文作者
论文摘要
医疗数据集通常面临稀缺性和数据失衡问题。此外，注释大型数据集以进行医学病变的语义分割是域知识和耗时的。在本文中，我们提出了一种新的对象混合方法（Short in Soft-CP），该方法结合了副本增强方法，用于离线医疗病变的语义分割，以确保出租时间周围的正确边缘信息，以解决上述问题。我们通过不同成像方式的几个数据集证明了该方法的有效性。在我们对Kits19 [2]数据集的实验中，软CP的表现优于现有的医疗病变合成方法。在低数据状态下（数据占数据占10％）和高数据制度（所有数据），在离线培训数据中，软CP的增长为 +26.5％的DSC（数据占数据的10％）和 +10.2％的DSC，真实图像与合成图像的比率为3：1。
The medical datasets are usually faced with the problem of scarcity and data imbalance. Moreover, annotating large datasets for semantic segmentation of medical lesions is domain-knowledge and time-consuming. In this paper, we propose a new object-blend method(short in soft-CP) that combines the Copy-Paste augmentation method for semantic segmentation of medical lesions offline, ensuring the correct edge information around the lession to solve the issue above-mentioned. We proved the method's validity with several datasets in different imaging modalities. In our experiments on the KiTS19[2] dataset, Soft-CP outperforms existing medical lesions synthesis approaches. The Soft-CP augementation provides gains of +26.5% DSC in the low data regime(10% of data) and +10.2% DSC in the high data regime(all of data), In offline training data, the ratio of real images to synthetic images is 3:1.
