A novel channel invariant architecture for the segmentation of cells and nuclei in multiplexed images using InstanSeg
This article has been Reviewed by the following groups
Listed in
- Evaluated articles (Arcadia Science)
Abstract
The quantitative analysis of bioimaging data increasingly depends on the accurate segmentation of cells and nuclei, a significant challenge for the analysis of high-plex imaging data. Current deep learning-based approaches to segment cells in multiplexed images require reducing the input to a small and fixed number of input channels, discarding imaging information in the process. We present Channel Net, a novel deep learning architecture for generating three-channel representations of multiplexed images irrespective of the number or ordering of imaged biomarkers. When combined with InstanSeg, ChannelNet sets a new benchmark for the segmentation of cells and nuclei on public multiplexed imaging datasets. We provide an open implementation of our method and integrate it in open source software. Our code and models are available on https://github.com/instanseg/instanseg .
Article activity feed
-
Assigning individual nuclei to their respective cells is a non-trivial and often ignored issue in cell segmentation.
Fully agree! Would it be possible to add references to alternative approaches? I am also curious if you considered revising the segmentation based on unmatched nuclei. One could argue that the isolated nucleus in Fig. 2 should be re-labeled as not a nucleus.
-
we resize images to 0.5 microns per pixel, as required by the models
As required by both models? Would it be possible to comment briefly on to what extent InstanSeg is scale-invariant?
-
randomly assigning primary and secondary colours to each of the input channels
Is the RGB projection truly random or are the colors evenly spaced?
-
During training, we only compute and backpropagate the loss using whichever labels are present in the ground truth. This method allows for the simultaneous prediction of nucleus and cell labels even when paired labels are not present in the ground truth.
Is the ground truth training data balanced between nucleus and cell labels or is this not necessary?
-
