Due to the contradiction of medical image processing, that is, the application of medical images is more and more widely and the limitation of medical images is difficult to label, few-shot learning technology has begun to receive more attention in the field of medical image processing. This paper proposes a Cross-Reference Transformer for medical image segmentation, which addresses the lack of interaction between the existing Cross-Reference support image and the query image. It can better mine and enhance the similar parts of support features and query features in high-dimensional channels. Experimental results show that the proposed model achieves good results on both CT dataset and MRI dataset.

翻译：由于医学图像处理中存在的矛盾——即医学图像的应用日益广泛，但医学图像的标注却受到限制且困难重重，小样本学习技术开始在医学图像处理领域受到更多关注。本文提出了一种用于医学图像分割的跨引变换器，解决了现有跨引支持图像与查询图像之间缺乏交互的问题，能够更好地挖掘并增强高维通道中支持特征与查询特征的相似部分。实验结果表明，所提出的模型在CT数据集和MRI数据集上均取得了良好的效果。