Learning with minimal effort: leveraging in silico labeling for cell and nucleus segmentation
Résumé
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.
Mots clés
Segmentation Transfer learning Pretext task In Silico Labeling Fluorescence microscopy
Segmentation
Transfer learning
Pretext task
In Silico Labeling
Fluorescence microscopy
Image and Video Processing (eess.IV)
Computer Vision and Pattern Recognition (cs.CV)
FOS: Electrical engineering
electronic engineering
information engineering
FOS: Computer and information sciences
Fichier principal
Bonte et al. - 2023 - Learning with minimal effort leveraging in silico.pdf (8.52 Mo)
Télécharger le fichier
Origine | Fichiers produits par l'(les) auteur(s) |
---|