arXiv 2412.198712024-12-27cs.CVcs.LG

邻居确实重要：面向医学半监督分割的密度感知对比学习

Neighbor Does Matter: Density-Aware Contrastive Learning for Medical Semi-supervised Segmentation

Monash University（莫纳什大学）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）；UNC-Chapel Hill（北卡罗来纳大学教堂山分校）

Feilong Tang, Zhongxing Xu, Ming Hu, Wenxue Li, Peng Xia, Yiheng Zhong, Hanjun Wu, Jionglong Su, Zongyuan Ge

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对医学多器官半监督分割中标签不足与软组织对比度低的问题，提出密度感知对比学习策略，利用特征密度定位稀疏区域并将锚定特征推向高密度簇中心，结合标签协同训练与几何正则化，在公开数据集上取得优于现有方法的分割性能。

摘要：

在医学图像分析中，多器官半监督分割面临标签不足和软组织对比度低等挑战。为解决这些问题，现有研究通常采用基于伪标签和一致性正则化的半监督分割技术。然而，这些方法主要依赖单个数据样本进行训练，忽略了特征空间中丰富的邻域信息。在本工作中，我们认为监督信息可以直接从特征空间的几何结构中提取。受基于密度的聚类假设启发，我们提出利用特征密度来定位特征簇中的稀疏区域。我们的目标是通过解决稀疏性问题来增强类内紧凑性。为此，我们提出了一种密度感知对比学习（DACL）策略，将稀疏区域中的锚定特征推向由高密度正样本近似的簇中心，从而形成更紧凑的簇。具体而言，我们的方法利用有标签和无标签数据样本构建密度感知邻居图，以估计特征密度并定位稀疏区域。我们还将标签引导的协同训练与密度引导的几何正则化相结合，为无标签数据形成互补监督。在Multi-Organ Segmentation Challenge数据集上的实验表明，我们提出的方法优于最先进的方法，凸显了其在医学图像分割任务中的有效性。

英文摘要：

In medical image analysis, multi-organ semi-supervised segmentation faces challenges such as insufficient labels and low contrast in soft tissues. To address these issues, existing studies typically employ semi-supervised segmentation techniques using pseudo-labeling and consistency regularization. However, these methods mainly rely on individual data samples for training, ignoring the rich neighborhood information present in the feature space. In this work, we argue that supervisory information can be directly extracted from the geometry of the feature space. Inspired by the density-based clustering hypothesis, we propose using feature density to locate sparse regions within feature clusters. Our goal is to increase intra-class compactness by addressing sparsity issues. To achieve this, we propose a Density-Aware Contrastive Learning (DACL) strategy, pushing anchored features in sparse regions towards cluster centers approximated by high-density positive samples, resulting in more compact clusters. Specifically, our method constructs density-aware neighbor graphs using labeled and unlabeled data samples to estimate feature density and locate sparse regions. We also combine label-guided co-training with density-guided geometric regularization to form complementary supervision for unlabeled data. Experiments on the Multi-Organ Segmentation Challenge dataset demonstrate that our proposed method outperforms state-of-the-art methods, highlighting its efficacy in medical image segmentation tasks.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。