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.
Images
Images of 32,266 asynchronously growing Jurkat cells were captured with the ImageStream platform. The cells were fixed and stained with PI (propidium iodide) to quantify DNA content and a MPM2 (mitotic protein monoclonal #2) antibody to identify mitotic cells.
The dataset consists of 32266 single cell images. For each cell we provide the current cell phase: G1, S, G2, prophase, metaphase, anaphase, telophase.
Eulenberg, P., Köhler, N., Blasi, T. et al. Reconstructing cell cycle and disease progression using deep learning. Nat Commun8, 463 (2017). https://doi.org/10.1038/s41467-017-00623-3
For more information
The image set was generated by the Flow Cytometry Core Facility (FCCF) at Newcastle University, Newcastle-upon-Tyne, UK. Please contact Andrew Filby regarding this dataset.