通过一致性与差异性学习，提升医学图像分割的半监督性能
Boosting Semi-Supervised Medical Image Segmentation via Masked Image Consistency and Discrepancy Learning
- 设计三模块框架，利用掩码输入增强上下文感知和小样本学习
- 在AMOS和Synapse数据集上达到当前最优，提升显著
- 适合需要高效利用少量标注数据的医学图像分割研究者
半监督学习在医学图像分割中具有重要意义，可通过利用未标注数据提升性能。现有方法多关注网络初始化差异和伪标签生成，却忽视了信息交互与模型多样性之间的平衡。本文提出掩码图像一致性与差异性学习（MICD）框架，包含三个核心模块：掩码交叉伪一致性（MCPC）模块通过掩码输入分支间的伪标签增强上下文感知与小样本学习能力；交叉特征一致性（CFC）模块通过保证解码器特征一致，强化信息交换与模型鲁棒性；交叉模型差异（CMD）模块利用指数移动平均教师网络监控输出并保持分支多样性。该框架聚焦细粒度局部信息，并在异构结构中维持模型多样性。在两个公开医学图像数据集AMOS和Synapse上的实验表明，该方法优于现有最先进方法。
原文摘要 · Abstract (English)
Semi-supervised learning is of great significance in medical image segmentation by exploiting unlabeled data. Among its strategies, the co-training framework is prominent. However, previous co-training studies predominantly concentrate on network initialization variances and pseudo-label generation, while overlooking the equilibrium between information interchange and model diversity preservation. In this paper, we propose the Masked Image Consistency and Discrepancy Learning (MICD) framework with three key modules. The Masked Cross Pseudo Consistency (MCPC) module enriches context perception and small sample learning via pseudo-labeling across masked-input branches. The Cross Feature Consistency (CFC) module fortifies information exchange and model robustness by ensuring decoder feature consistency. The Cross Model Discrepancy (CMD) module utilizes EMA teacher networks to oversee outputs and preserve branch diversity. Together, these modules address existing limitations by focusing on fine-grained local information and maintaining diversity in a heterogeneous framework. Experiments on two public medical image datasets, AMOS and Synapse, demonstrate that our approach outperforms state-of-the-art methods.
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。