Segmenting nuclei in brightfield images with neural networks
Fishman, D.; Salumaa, S.-O.; Majoral, D.; Peel, S.; Wildenhain, J.; Schreiner, A.; Palo, K.; Parts, L.
Show abstract
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.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- RETINA: Reconstruction-based Pre-Trained Enhanced TransUNet for Electron Microscopy Segmentation on the CEM500K Dataset 96%
- Deep learning tools and modeling to estimate the temporal expression of cell cycle proteins from 2D still images 96%
- DeLTA: Automated cell segmentation, tracking, and lineage reconstruction using deep learning 95%
Similar papers in this journal
- Digitally Predicting Protein Localization and Manipulating Protein Activity in Fluorescence Images Using Four-dimensional Reslicing GAN 94%
- CyAnno: A semi-automated approach for cell type annotation of mass cytometry datasets 94%
- Quantifying and correcting slide-to-slide variation in multiplexed immunofluorescence images 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.