Classification of High Content Screening Data by Deep Convolutional Neural Networks

In drug discovery, high content screening (HCS) is an imaging-based method forcell-based screening of large libraries of drug compounds. HCS generates enormous amounts of images that need to be analysed and quantified by automated image analysis. This analysis is typically performed by a variety of algorithms segmenting cells and sub-cellular compartments and quantifying properties such as fluorescence intensities, morphological features, and textural characteristics. These quantified data can then be used to train a classifier to classify the imaged cells according to the phenotypic effects of the compounds. Recent developments in machine learning have enabled a new kind of image analysis in which classifiers based on convolutional neural networks can be trained on the image data directly, by passing the image quantification step. This has been shown to produce highly accurate predictions and simplify the analysis process. In this study, convolutional neural networks (CNNs) were used to classify HCS images of cells treated with a set of different drug compounds. A set of network architectures and hyper-parameters were explored in order to optimise the classification performance. The results were compared with the accuracies achieved with a classical image analysis pipeline in combination with a classifier. With this data set, the best CNN-based classifier achieved an accuracy of 91.3 %, where as classical image analysis combined with a random forest classifier achieved a classification accuracy of 78.8 %. In addition to the large increase in classification accuracy, CNNs have benefits such as being less biased when it comes to image quantification algorithm selection, and require less hands-on time during optimisation.