Kraus Oren Z, Ba Jimmy Lei, Frey Brendan J
Department of Electrical and Computer Engineering, University of Toronto, Toronto, M5S 2E4, Canada The Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, M5S 3E1, Canada.
Department of Electrical and Computer Engineering, University of Toronto, Toronto, M5S 2E4, Canada.
Bioinformatics. 2016 Jun 15;32(12):i52-i59. doi: 10.1093/bioinformatics/btw252.
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.
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.
Torch7 implementation available upon request.
高内涵筛选（HCS）技术已使大规模成像实验能够用于细胞生物学研究和药物筛选。这些系统每天会生成数十万张显微镜图像，其效用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在目标识别挑战中占据主导地位。这些任务通常每张图像有一个居中的单个目标，现有模型并不直接适用于显微镜数据集。在此，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，以便仅使用全图像级注释对显微镜图像进行分类和分割。
我们引入了一种新的神经网络架构，该架构使用MIL对含有细胞群体的显微镜图像同时进行分类和分割。我们的方法基于MIL中使用的聚合函数与CNN中使用的池化层之间的相似性。为便于在CNN特征图中对大量实例进行聚合，我们提出了噪声与（Noisy-AND）池化函数，这是一种对异常值具有鲁棒性的新MIL算子。将CNN与MIL相结合能够使用带有图像级标签的全显微镜图像来训练CNN。我们表明，在哺乳动物和酵母数据集上，端到端训练的MIL CNN优于之前的几种方法，且无需任何分割步骤。
如有需要可提供Torch7实现。
