Visualising uncertainty in brightfield to fluorescent image inference with BFNet
Warchal, S.; Gautier, C.; Dorval, T.; Stephan, J.-P.
Show abstract
Predicting fluorescently labelled cellular structures from brightfield images is a recent application of convolutional neural networks and has already proven a valuable tool in biological imaging studies. These methods reduce the need for time-consuming manual annotations for supervised datasets, potentially reduce the costs in high-throughput imaging screens, and open up a number of potentially novel analyses. However as with any prediction there can be sources of error and uncertainty. Here we present BFNet, a method to visualise the uncertainty in predicted images by applying Monte Carlo dropout during inference and calculating per-pixel variance as an uncertainty map. Our method demonstrates the ability to highlight regions of an image where prediction is difficult or impossible due to imaging artefacts such as occlusions or out-of-focus images, as well as more general uncertainty when a trained model is applied to new data from different imaging of experimental settings. We have provided a python implementation of the method which is available at github.com/swarchal/bfnet.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Stitching and registering highly multiplexed whole slide images of tissues and tumors using ASHLAR 93%
- Digitally Predicting Protein Localization and Manipulating Protein Activity in Fluorescence Images Using Four-dimensional Reslicing GAN 92%
- NIEND: Neuronal Image Enhancement through Noise Disentanglement 92%
Similar papers in this journal
Similar papers in this journal
- InstantDL - An easy-to-use deep learning pipeline for image segmentation and classification 93%
- LLAMA: a robust and scalable machine learning pipeline for analysis of cellsurface projections in large scale 4D microscopy data 92%
- Multi-Template Matching: a versatile tool for object-localization in microscopy images 92%
"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.