Sample-Based Training Data For Effective 3D Cell Segmentation
Smith, A.; Bretschneider, T.
Show abstract
Deep learning remains the leading choice for cell segmentation, a critical step in bioimaging analysis. Whilst deep learning models provide excellent segmentation accuracy, a large number of hand-annotated samples are required which are scarce in 3D. We propose a method for generating synthetic data for training deep learning models to augment or replace such datasets. By preserving key features in real data, we show that a standard UNet trained on synthetic data can segment single motile cells with branching filopodia with high accuracy. We also demonstrate how low-effort slice annotations can sufficiently replace volume annotations in our data generation pipeline. Overall, we provide a simple alternative to annotating large 3D datasets for training neural networks to segment cell imaging data.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Shape-to-graph Mapping Method for Efficient Characterization and Classification of Complex Geometries in Biological Images 95%
- A Deep Learning approach for time-consistent cell cycle phase prediction from microscopy data 94%
- Comparing a computational model of visual problem solving with human vision on a difficult vision task. 94%
Similar papers in this journal
- Caveolae and scaffold detection from single molecule localization microscopy data using deep learning 95%
- Detection and measurement of butterfly eyespot and spot patterns using convolutional neural networks 95%
- ConfluentFUCCI for fully-automated analysis of cell-cycle progression in a highly dense collective of migrating cells 94%
Similar papers in this journal
"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.