带有像素依赖噪声标签的不平衡医学图像分割
Imbalanced Medical Image Segmentation with Pixel-dependent Noisy Labels
AI总结：
针对医学图像分割中像素依赖噪声标签与类别不平衡问题，提出CLCS框架，通过双分支协同学习、课程动态阈值选样及噪声平衡损失提升分割性能。
摘要：
由于医学图像标注存在难度，训练数据中的噪声标签往往会阻碍精准的医学图像分割。现有针对噪声标签的研究通常做出类别依赖的假设，忽略了大多数噪声标签具备像素依赖的特性。此外，现有方法一般采用固定阈值过滤噪声标签，存在移除少数类的风险，进而会降低分割性能。为弥补这些研究空白，我们提出的框架——课程选择协同学习（Collaborative Learning with Curriculum Selection，CLCS），可解决存在类别不平衡的像素依赖噪声标签问题。CLCS在现有研究基础上实现了三方面推进：其一，将噪声标签视为像素依赖的，并通过协同学习框架处理该问题；其二，采用适配模型学习进度的课程动态阈值方法筛选干净数据样本，以缓解类别不平衡问题；其三，对噪声数据样本应用噪声平衡损失以提升数据利用率，而非直接丢弃这些样本。具体而言，我们的CLCS包含两个模块：课程噪声标签样本选择（Curriculum Noisy Label Sample Selection，CNS）和噪声平衡损失（Noise Balance Loss，NBL）。在CNS模块中，我们设计了带有差异损失的双分支网络用于协同学习，从而可从不同视角提取同一实例的不同特征表示，并用于投票确定像素的类别概率。此外，该模块还采用课程动态阈值，通过概率投票筛选带有干净标签的样本。在NBL模块中，我们并未直接丢弃疑似存在噪声的标签，而是进一步采用一种鲁棒损失函数来利用这类实例以提升性能。
英文摘要：
Accurate medical image segmentation is often hindered by noisy labels in training data, due to the challenges of annotating medical images. Prior research works addressing noisy labels tend to make class-dependent assumptions, overlooking the pixel-dependent nature of most noisy labels. Furthermore, existing methods typically apply fixed thresholds to filter out noisy labels, risking the removal of minority classes and consequently degrading segmentation performance. To bridge these gaps, our proposed framework, Collaborative Learning with Curriculum Selection (CLCS), addresses pixel-dependent noisy labels with class imbalance. CLCS advances the existing works by i) treating noisy labels as pixel-dependent and addressing them through a collaborative learning framework, and ii) employing a curriculum dynamic thresholding approach adapting to model learning progress to select clean data samples to mitigate the class imbalance issue, and iii) applying a noise balance loss to noisy data samples to improve data utilization instead of discarding them outright. Specifically, our CLCS contains two modules: Curriculum Noisy Label Sample Selection (CNS) and Noise Balance Loss (NBL). In the CNS module, we designed a two-branch network with discrepancy loss for collaborative learning so that different feature representations of the same instance could be extracted from distinct views and used to vote the class probabilities of pixels. Besides, a curriculum dynamic threshold is adopted to select clean-label samples through probability voting. In the NBL module, instead of directly dropping the suspiciously noisy labels, we further adopt a robust loss to leverage such instances to boost the performance.
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。
