Abstract
Few-Shot Medical Image Segmentation (FSMIS) aims to segment novel classes of medical objects using only a few labeled images. Prototype-based methods have made significant progress in addressing FSMIS. However, they typically generate a single global prototype for the support image to match with the query image, overlooking intra-class variations. To address this issue, we propose a Self-guided Prototype Enhancement Network (SPENet). Specifically, we introduce a Multi-level Prototype Generation (MPG) module, which enables multi-granularity measurement between the support and query images by simultaneously generating a global prototype and an adaptive number of local prototypes. Additionally, we observe that not all local prototypes in the support image are beneficial for matching, especially when there are substantial discrepancies between the support and query images. To alleviate this issue, we propose a Query-guided Local Prototype Enhancement (QLPE) module, which adaptively refines support prototypes by incorporating guidance from the query image, thus mitigating the negative effects of such discrepancies. Extensive experiments on three public medical datasets demonstrate that SPENet outperforms existing state-of-the-art methods, achieving superior performance.
Abstract (translated)
少样本医学图像分割（FSMIS）的目标是仅使用少量标注图像来对新型的医学对象进行分割。基于原型的方法在解决FSMIS问题上取得了显著进展，但它们通常为支持图像生成单一全局原型与查询图像匹配，从而忽略了类内的变化。为了应对这一挑战，我们提出了一种自我引导的原型增强网络（SPENet）。具体来说，我们引入了一个多层次原型生成（MPG）模块，该模块通过同时生成全局原型和自适应数量的局部原型，使得支持图像和查询图像之间可以进行多粒度测量。此外，我们观察到并非支持图像中的所有局部原型都对匹配有帮助，特别是在支持图像与查询图像之间存在显著差异的情况下更是如此。为缓解这一问题，我们提出了一种基于查询引导的局部原型增强（QLPE）模块，该模块通过从查询图像中获取指导信息来自适应地精炼支持原型，从而减轻这些差异所带来的负面影响。在三个公开医学数据集上的广泛实验表明，SPENet优于现有的最先进方法，在性能上取得了更好的结果。
URL
https://arxiv.org/abs/2509.02993
