用多个原型提升医学图像分割精度，更好区分同类像素差异。
Multi-Prototype Embedding Refinement for Semi-Supervised Medical Image Segmentation
- 为每类像素设计多个原型，捕捉内部细微差异。
- 在两个主流数据集上优于现有最先进方法，显著提升分割准确率。
- 适合需要高精度分割的医疗影像研究者使用。
医学图像分割旨在以体素级别识别解剖结构。分割精度依赖于区分体素间的差异。相较于对类别间差异的研究进展，类别内差异仍受关注不足。传统线性分类器因每类仅有一个可学习权重，难以捕捉此类细微差别。为此，我们提出一种基于多原型的嵌入优化方法，用于半监督医学图像分割。具体地，设计了一种多原型分类策略，从体素嵌入的结构关系角度重新思考分割任务。通过在每个类别中沿多个原型的分布对体素进行聚类，探索类别内变化。随后引入一致性约束，缓解线性分类器的局限性。该约束融合了线性分类器与所提原型分类器的不同分类粒度。在两个流行基准上的全面评估表明，该方法优于当前最先进的方法。代码已公开于 https://github.com/Briley-byl123/MPER。
原文摘要 · Abstract (English)
Medical image segmentation aims to identify anatomical structures at the voxel-level. Segmentation accuracy relies on distinguishing voxel differences. Compared to advancements achieved in studies of the inter-class variance, the intra-class variance receives less attention. Moreover, traditional linear classifiers, limited by a single learnable weight per class, struggle to capture this finer distinction. To address the above challenges, we propose a Multi-Prototype-based Embedding Refinement method for semi-supervised medical image segmentation. Specifically, we design a multi-prototype-based classification strategy, rethinking the segmentation from the perspective of structural relationships between voxel embeddings. The intra-class variations are explored by clustering voxels along the distribution of multiple prototypes in each class. Next, we introduce a consistency constraint to alleviate the limitation of linear classifiers. This constraint integrates different classification granularities from a linear classifier and the proposed prototype-based classifier. In the thorough evaluation on two popular benchmarks, our method achieves superior performance compared with state-of-the-art methods. Code is available at https://github.com/Briley-byl123/MPER.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。