IEEE Trans Med Imaging. 2017 Jul;36(7):1405-1417. doi: 10.1109/TMI.2017.2677479. Epub 2017 Mar 2.
In recently published clinical trial results, hypoxia-modified therapies have shown to provide more positive outcomes to cancer patients, compared with standard cancer treatments. The development and validation of these hypoxia-modified therapies depend on an effective way of measuring tumor hypoxia, but a standardized measurement is currently unavailable in clinical practice. Different types of manual measurements have been proposed in clinical research, but in this paper we focus on a recently published approach that quantifies the number and proportion of hypoxic regions using high resolution (immuno-)fluorescence (IF) and hematoxylin and eosin (HE) stained images of a histological specimen of a tumor. We introduce new machine learning-based methodologies to automate this measurement, where the main challenge is the fact that the clinical annotations available for training the proposed methodologies consist of the total number of normoxic, chronically hypoxic, and acutely hypoxic regions without any indication of their location in the image. Therefore, this represents a weakly-supervised structured output classification problem, where training is based on a high-order loss function formed by the norm of the difference between the manual and estimated annotations mentioned above. We propose four methodologies to solve this problem: 1) a naive method that uses a majority classifier applied on the nodes of a fixed grid placed over the input images; 2) a baseline method based on a structured output learning formulation that relies on a fixed grid placed over the input images; 3) an extension to this baseline based on a latent structured output learning formulation that uses a graph that is flexible in terms of the amount and positions of nodes; and 4) a pixel-wise labeling based on a fully-convolutional neural network. Using a data set of 89 weakly annotated pairs of IF and HE images from eight tumors, we show that the quantitative results of methods (3) and (4) above are equally competitive and superior to the naive (1) and baseline (2) methods. All proposed methodologies show high correlation values with respect to the clinical annotations.
在最近发表的临床试验结果中，与标准癌症治疗相比，缺氧修饰疗法显示出对癌症患者更积极的结果。这些缺氧修饰疗法的开发和验证依赖于有效测量肿瘤缺氧的方法，但目前在临床实践中还没有标准化的测量方法。在临床研究中已经提出了不同类型的手动测量方法，但在本文中，我们专注于最近发表的一种方法，该方法使用肿瘤组织学标本的高分辨率（免疫）荧光（IF）和苏木精和伊红（HE）染色图像来量化缺氧区域的数量和比例。我们引入了新的基于机器学习的方法来实现这种测量的自动化，其中主要的挑战是，为了训练所提出的方法而提供的临床注释仅包括正常氧合、慢性缺氧和急性缺氧区域的总数，而没有任何关于它们在图像中位置的指示。因此，这代表了一个弱监督的结构化输出分类问题，其中训练是基于由手动和估计注释之间的差的范数形成的高阶损失函数。我们提出了四种解决该问题的方法：1）一种使用固定网格上的多数分类器的简单方法；2）一种基于固定网格的结构化输出学习公式的基线方法；3）一种基于灵活节点数和位置的图的此基线方法的扩展；4）一种基于全卷积神经网络的像素级标记方法。使用来自 8 个肿瘤的 89 对弱注释的 IF 和 HE 图像数据集，我们表明方法（3）和（4）的定量结果与简单（1）和基线（2）方法一样具有竞争力，并且优于简单（1）和基线（2）方法。所有提出的方法都与临床注释具有高度相关性。
