PT  - JOURNAL ARTICLE
AU  - Dmytro Fishman
AU  - Sten-Oliver Salumaa
AU  - Daniel Majoral
AU  - Samantha Peel
AU  - Jan Wildenhain
AU  - Alexander Schreiner
AU  - Kaupo Palo
AU  - Leopold Parts
TI  - Segmenting nuclei in brightfield images with neural networks
AID  - 10.1101/764894
DP  - 2019 Jan 01
TA  - bioRxiv
PG  - 764894
4099  - http://biorxiv.org/content/early/2019/09/10/764894.short
4100  - http://biorxiv.org/content/early/2019/09/10/764894.full
AB  - Identifying nuclei is a standard first step to analysing cells in microscopy images. The traditional approach relies on signal from a DNA stain, or fluorescent transgene expression localised to the nucleus. However, imaging techniques that do not use fluorescence can also carry useful information. Here, we demonstrate that it is possible to accurately segment nuclei directly from brightfield images using deep learning. We confirmed that three convolutional neural network architectures can be adapted for this task, with U-Net achieving the best overall performance, Mask R-CNN providing an additional benefit of instance segmentation, and DeepCell proving too slow for practical application. We found that accurate segmentation is possible using as few as 16 training images and that models trained on images from similar cell lines can extrapolate well. Acquiring data from multiple focal planes further helps distinguish nuclei in the samples. Overall, our work liberates a fluorescence channel reserved for nuclear staining, thus providing more information from the specimen, and reducing reagents and time required for preparing imaging experiments.