Back to Search Start Over

Learning with minimal effort: leveraging in silico labeling for cell and nucleus segmentation

Authors :
Bonte, Thomas
Philbert, Maxence
Coleno, Emeline
Bertrand, Edouard
Imbert, Arthur
Walter, Thomas
Publication Year :
2023

Abstract

Deep learning provides us with powerful methods to perform nucleus or cell segmentation with unprecedented quality. However, these methods usually require large training sets of manually annotated images, which are tedious and expensive to generate. In this paper we propose to use In Silico Labeling (ISL) as a pretraining scheme for segmentation tasks. The strategy is to acquire label-free microscopy images (such as bright-field or phase contrast) along fluorescently labeled images (such as DAPI or CellMask). We then train a model to predict the fluorescently labeled images from the label-free microscopy images. By comparing segmentation performance across several training set sizes, we show that such a scheme can dramatically reduce the number of required annotations.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2301.03914
Document Type :
Working Paper