Learning with minimal effort: leveraging in silico labeling for cell and nucleus segmentation - Mines Paris Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

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.
Fichier principal
Vignette du fichier
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)

Dates et versions

hal-04396531 , version 1 (16-01-2024)

Identifiants

Citer

Thomas Bonte, Maxence Philbert, Emeline Coleno, Edouard Bertrand, Arthur Imbert, et al.. Learning with minimal effort: leveraging in silico labeling for cell and nucleus segmentation. 2024. ⟨hal-04396531⟩
10 Consultations
6 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More