Detecting overlapping instances in microscopy images using extremal region trees
Detecting overlapping instances in microscopy images using extremal region trees
复制标题
DOI：
10.1016/j.media.2015.03.002
复制
发表时间：
2016-01-01
影响因子：
10.9
通讯作者：
Zisserman, Andrew
中科院分区：
文献类型：
--
作者：
Arteta, Carlos;Lempitsky, Victor;Zisserman, Andrew
在许多显微镜应用中，图像可能包含低和高细胞密度的区域，对应于不同组织或不同生长阶段的菌落。这对大多数以前开发的自动细胞检测和计数方法提出了挑战，这些方法旨在处理低密度场景（通过细胞检测）或高密度场景（通过密度估计或纹理分析）。这项工作的目的是检测显微镜图像中感兴趣的物体的所有实例。实例可能部分重叠并聚集在一起。为此，我们引入了一个树状结构的离散图形模型，该模型用于通过分类分数的全局优化来选择和标记图像中的一组非重叠区域。每个区域都用它包含的实例数量来标记，例如，可以通过在检测过程中为对象元组定义单独的类来选择包含两个或三个对象实例的区域。我们表明，该公式可以在结构化输出支持向量机框架内学习，并且该模型中的推理可以使用树状结构区域图上的动态规划来完成。此外，学习只需要对每个实例上的一个点进行弱注释。选择的候选区域作为从显微镜图像中计算的曲面的极值区域，并且我们表明，通过考虑代理问题来学习曲面，可以更好地选择极值区域，从而提高模型的性能。此外，我们考虑了结构化输出学习中使用的损失函数的一些变化。该模型在六个完全不同的图像数据集上应用和评估：荧光显微镜，弱荧光分子图像，相衬显微镜和组织病理学图像，并且在性能上显示出超过最先进的状态。(C) 2015 Elsevier B.V.版权所有
In many microscopy applications the images may contain both regions of low and high cell densities corresponding to different tissues or colonies at different stages of growth. This poses a challenge to most previously developed automated cell detection and counting methods, which are designed to handle either the low-density scenario (through cell detection) or the high-density scenario (through density estimation or texture analysis).The objective of this work is to detect all the instances of an object of interest in microscopy images. The instances may be partially overlapping and clustered. To this end we introduce a tree-structured discrete graphical model that is used to select and label a set of non-overlapping regions in the image by a global optimization of a classification score. Each region is labeled with the number of instances it contains for example regions can be selected that contain two or three object instances, by defining separate classes for tuples of objects in the detection process.We show that this formulation can be learned within the structured output SVM framework and that the inference in such a model can be accomplished using dynamic programming on a tree structured region graph. Furthermore, the learning only requires weak annotations a dot on each instance. The candidate regions for the selection are obtained as extremal region of a surface computed from the microscopy image, and we show that the performance of the model can be improved by considering a proxy problem for learning the surface that allows better selection of the extremal regions. Furthermore, we consider a number of variations for the loss function used in the structured output learning.The model is applied and evaluated over six quite disparate data sets of images covering: fluorescence microscopy, weak-fluorescence molecular images, phase contrast microscopy and histopathology images, and is shown to exceed the state of the art in performance. (C) 2015 Elsevier B.V. All rights reserved.