Skip to Main content Skip to Navigation
New interface
Journal articles

Domain Adapted Multi-task Learning For Segmenting Amoeboid Cells in Microscopy

Abstract : The method proposed in this paper is a robust combination of multi-task learning and unsupervised domain adaptation for segmenting amoeboid cells in microscopy. A highlight of this work is the manner in which the model’s hyperparameters are estimated. The detriments of ad-hoc parameter estimation are well known, but this issue remains largely unaddressed in the context of CNN-based segmentation. Using a novel min-max formulation of the segmentation cost function our proposed method analytically estimates the model’s hyperparameters, while simultaneously learning the CNN weights during training. This end-to-end framework provides a consolidated mechanism to harness the potential of multi-task learning to isolate and segment clustered cells from low contrast brightfield images, and it simultaneously leverages deep domain adaptation to segment fluorescent cells without explicit pixel-level re-annotation of the data. Experimental validations on multi-cellular images strongly suggest the effectiveness of the proposed technique, and our quantitative results show at least 15% and 10% improvement in cell segmentation on brightfield and fluorescence images respectively compared to contemporary supervised segmentation methods.
Document type :
Journal articles
Complete list of metadata

https://hal-pasteur.archives-ouvertes.fr/pasteur-03812027
Contributor : Elisabeth Labruyere Connect in order to contact the contributor
Submitted on : Wednesday, October 12, 2022 - 1:11:33 PM
Last modification on : Saturday, October 15, 2022 - 4:41:04 AM

Identifiers

Collections

Citation

Suvadip Mukherjee, Rituparna Sarkar, Maria Manich, Elisabeth Labruyere, Jean-Christophe Olivo-Marin. Domain Adapted Multi-task Learning For Segmenting Amoeboid Cells in Microscopy. IEEE Transactions on Medical Imaging, 2022, pp.1-1. ⟨10.1109/TMI.2022.3203022⟩. ⟨pasteur-03812027⟩

Share

Metrics

Record views

0