Classifying and segmenting microscopy images with deep multiple instance learning.
Classifying and segmenting microscopy images with deep multiple instance learning.
复制标题
DOI：
10.1093/bioinformatics/btw252
复制
发表时间：
2016-06-15
期刊：
影响因子：
--
通讯作者：
Frey BJ
中科院分区：
文献类型：
--
作者：
Kraus OZ;Ba JL;Frey BJ
动机：高内涵筛选（HCS）技术使大规模成像实验研究细胞生物学和药物筛选。这些系统每天产生数十万张显微图像，其实用性取决于自动图像分析。最近，直接从像素强度值学习特征表示的深度学习方法已经主导了对象识别挑战。这些任务通常每个图像具有单个居中对象，并且现有模型不直接适用于显微镜数据集。在这里，我们开发了一种将深度卷积神经网络（CNN）与多实例学习（MIL）相结合的方法，以便仅使用整个图像级别的注释对显微镜图像进行分类和分割。结果如下：我们引入了一种新的神经网络架构，该架构使用MIL同时对显微图像和细胞群进行分类和分割。我们的方法基于MIL中使用的聚合函数和CNN中使用的池化层之间的相似性。为了便于在CNN特征图中聚合大量实例，我们提出了Noisy-AND池化函数，这是一种新的MIL算子，对离群值具有鲁棒性。将CNN与MIL相结合，可以使用带有图像级标签的整个显微图像来训练CNN。我们表明，在哺乳动物和酵母数据集上，训练端到端MIL CNN的性能优于之前的几种方法，而不需要任何分割步骤。可用性和实施：可应要求提供Torch 7实施。联系人：oren. mail.utoronto.ca
Motivation: High-content screening (HCS) technologies have enabled large scale imaging experiments for studying cell biology and for drug screening. These systems produce hundreds of thousands of microscopy images per day and their utility depends on automated image analysis. Recently, deep learning approaches that learn feature representations directly from pixel intensity values have dominated object recognition challenges. These tasks typically have a single centered object per image and existing models are not directly applicable to microscopy datasets. Here we develop an approach that combines deep convolutional neural networks (CNNs) with multiple instance learning (MIL) in order to classify and segment microscopy images using only whole image level annotations. Results: We introduce a new neural network architecture that uses MIL to simultaneously classify and segment microscopy images with populations of cells. We base our approach on the similarity between the aggregation function used in MIL and pooling layers used in CNNs. To facilitate aggregating across large numbers of instances in CNN feature maps we present the Noisy-AND pooling function, a new MIL operator that is robust to outliers. Combining CNNs with MIL enables training CNNs using whole microscopy images with image level labels. We show that training end-to-end MIL CNNs outperforms several previous methods on both mammalian and yeast datasets without requiring any segmentation steps. Availability and implementation: Torch7 implementation available upon request. Contact: oren.kraus@mail.utoronto.ca