通过融合通道注意力与域对抗训练提升用于分割的 CNN 的染色不变性
Improving Stain Invariance of CNNs for Segmentation by Fusing Channel Attention and Domain-Adversarial Training
AI总结：
针对计算病理图像染色差异导致的分割泛化问题，提出融合通道注意力与染色对抗训练的 CNN 方法，并在多中心数据集上验证其显著提升。
摘要：
染色方案的差异，例如不同的切片制备技术、化学试剂和扫描仪配置，可能产生多种多样的全切片图像（WSIs）。这种分布偏移会对深度学习模型在未见样本上的性能产生负面影响，为开发新的计算病理学应用带来重大挑战。在本研究中，我们提出一种方法，用于在单源设置下提升卷积神经网络（CNN）针对语义分割任务中染色变化的泛化能力。近期研究表明，风格特征主要以协方差形式存在于网络较早层中。基于这些发现，我们设计了一种通道注意力机制，用于检测染色特有特征，并修改了此前提出的染色不变训练方案。我们对较早层的输出进行重新加权，并将其传递给染色对抗训练分支。我们在多中心、多染色数据集上评估了该方法，并通过可解释性分析证明了其有效性。按照多种评价指标衡量，我们的方法相比基线取得了显著提升，并且与其他方法相比具有具有竞争力的性能。我们还表明，将该方法与染色增强相结合可产生互利结果，并优于其他技术。总体而言，本研究为计算病理学领域作出了重要贡献。
英文摘要：
Variability in staining protocols, such as different slide preparation techniques, chemicals, and scanner configurations, can result in a diverse set of whole slide images (WSIs). This distribution shift can negatively impact the performance of deep learning models on unseen samples, presenting a significant challenge for developing new computational pathology applications. In this study, we propose a method for improving the generalizability of convolutional neural networks (CNNs) to stain changes in a single-source setting for semantic segmentation. Recent studies indicate that style features mainly exist as covariances in earlier network layers. We design a channel attention mechanism based on these findings that detects stain-specific features and modify the previously proposed stain-invariant training scheme. We reweigh the outputs of earlier layers and pass them to the stain-adversarial training branch. We evaluate our method on multi-center, multi-stain datasets and demonstrate its effectiveness through interpretability analysis. Our approach achieves substantial improvements over baselines and competitive performance compared to other methods, as measured by various evaluation metrics. We also show that combining our method with stain augmentation leads to mutually beneficial results and outperforms other techniques. Overall, our study makes significant contributions to the field of computational pathology.
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。
