Abstract
We show that deep convolutional neural networks combined with nonlinear dimension reduction enable reconstructing biological processes based on raw image data. We demonstrate this by reconstructing the cell cycle of Jurkat cells and disease progression in diabetic retinopathy. In further analysis of Jurkat cells, we detect and separate a subpopulation of dead cells in an unsupervised manner and, in classifying discrete cell cycle stages, we reach a sixfold reduction in error rate compared to a recent approach based on boosting on image features. In contrast to previous methods, deep learning based predictions are fast enough for on-the-fly analysis in an imaging flow cytometer.
Highlights
We show that deep convolutional neural networks combined with nonlinear dimension reduction enable reconstructing biological processes based on raw image data
We focus on imaging data from fluorescence microscopy[1], in particular from imaging flow cytometry (IFC), which combines the fluorescence sensitivity and high-throughput capabilities of flow cytometry with single-cell imaging[2]
Imaging flow cytometry is unusually well-suited to deep learning as it provides very high sample numbers and image data from several channels, that is, high dimensional, spatially correlated data
Summary
We show that deep convolutional neural networks combined with nonlinear dimension reduction enable reconstructing biological processes based on raw image data. We demonstrate this by reconstructing the cell cycle of Jurkat cells and disease progression in diabetic retinopathy. The detailed quantitative information necessary for a continuous label is usually only available if a phenomenon is already understood on a molecular level and markers that quantitatively characterize the phenomenon are available While this is possible for cell cycle when carrying out elaborate experiments where such markers are measured[5, 8], in many other cases, this is too tedious, has severe side effects with unwanted influences on the phenomenon itself or is not possible as markers for a specific phenomenon are not known. We propose a general workflow that uses a deep convolutional neural network combined with classification and visualization based on nonlinear dimension reduction (Fig. 1)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
