用于减少组织病理学图像搜索偏置的排序损失与隔离学习
Ranking Loss and Sequestering Learning for Reducing Image Search Bias in Histopathology
AI总结：
本文针对组织病理学图像搜索中的偏置与泛化问题，提出排序损失函数和隔离学习两种方法，以匹配导向方式优化特征提取并减少机构偏置，在最大全切片图像公共数据集上验证了优于现有方法的性能。
摘要：
近年来，深度学习开始在医疗健康应用中发挥重要作用，其中包括数字病理学中的图像搜索。尽管计算机视觉近期取得了进展，但在组织病理学档案中进行图像搜索仍存在显著问题。一个众所周知的问题是人工智能偏置和泛化能力不足。深度模型的一个更具体的缺陷是对搜索功能的忽视。前者影响所有模型，后者仅影响搜索和匹配。由于缺乏基于排序的学习，研究人员必须基于分类误差训练模型，然后将得到的嵌入用于图像搜索目的。此外，即使使用来自多家医院的大型图像库，深度模型似乎也容易产生内部偏置。本文提出两个新思路来提升图像搜索性能。首先，我们使用排序损失函数引导特征提取朝着搜索的匹配导向特性发展。通过迫使模型学习匹配输出的排序，表示学习被定制为面向图像搜索，而不是学习类别标签。其次，我们引入隔离学习的概念以增强特征提取的泛化能力。通过将输入医院的图像从匹配输出中排除，即隔离输入域，从而减少机构偏置。所提出的思路在最大的全切片图像公共数据集上进行了实现和验证。实验结果表明，与当前最先进方法相比，取得了更优的结果。
英文摘要：
Recently, deep learning has started to play an essential role in healthcare applications, including image search in digital pathology. Despite the recent progress in computer vision, significant issues remain for image searching in histopathology archives. A well-known problem is AI bias and lack of generalization. A more particular shortcoming of deep models is the ignorance toward search functionality. The former affects every model, the latter only search and matching. Due to the lack of ranking-based learning, researchers must train models based on the classification error and then use the resultant embedding for image search purposes. Moreover, deep models appear to be prone to internal bias even if using a large image repository of various hospitals. This paper proposes two novel ideas to improve image search performance. First, we use a ranking loss function to guide feature extraction toward the matching-oriented nature of the search. By forcing the model to learn the ranking of matched outputs, the representation learning is customized toward image search instead of learning a class label. Second, we introduce the concept of sequestering learning to enhance the generalization of feature extraction. By excluding the images of the input hospital from the matched outputs, i.e., sequestering the input domain, the institutional bias is reduced. The proposed ideas are implemented and validated through the largest public dataset of whole slide images. The experiments demonstrate superior results compare to the-state-of-art.
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。
