用于组织病理学图像分析的染色不变自监督学习
Stain-invariant self supervised learning for histopathology image analysis
AI总结：
提出一种针对乳腺癌H&E染色图像的染色不变自监督学习算法，通过在潜在空间中利用染色归一化技术施加约束，提升了对染色变化的鲁棒性和分类性能，并在多个公开乳腺癌数据集上达到最先进水平。
摘要：
我们提出了一种自监督算法，用于乳腺癌的苏木精-伊红（H&E）染色图像中的多项分类任务。我们的方法对组织学图像采集过程中固有的染色变化具有鲁棒性，而这种变化限制了自动化分析工具的适用性。我们通过在训练期间利用染色归一化技术对学习到的潜在空间施加约束来解决这个问题。在每次迭代中，我们选择一张图像作为归一化目标，并生成批次中每张图像归一化到该目标的版本。我们最小化对应于不同染色变化下同一图像的嵌入之间的距离，同时最大化其他样本之间的距离。我们展示了通过在各种归一化目标和方法上的广泛实验，我们的方法不仅提高了对多中心数据染色变化的鲁棒性，而且提高了分类性能。我们的方法在几个公开可用的乳腺癌数据集上实现了最先进的性能，范围从肿瘤分类（CAMELYON17）和亚型分类（BRACS）到HER2状态分类和治疗反应预测。
英文摘要：
We present a self-supervised algorithm for several classification tasks within hematoxylin and eosin (H&E) stained images of breast cancer. Our method is robust to stain variations inherent to the histology images acquisition process, which has limited the applicability of automated analysis tools. We address this problem by imposing constraints a learnt latent space which leverages stain normalization techniques during training. At every iteration, we select an image as a normalization target and generate a version of every image in the batch normalized to that target. We minimize the distance between the embeddings that correspond to the same image under different staining variations while maximizing the distance between other samples. We show that our method not only improves robustness to stain variations across multi-center data, but also classification performance through extensive experiments on various normalization targets and methods. Our method achieves the state-of-the-art performance on several publicly available breast cancer datasets ranging from tumor classification (CAMELYON17) and subtyping (BRACS) to HER2 status classification and treatment response prediction.
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。
