Helmholtz Gemeinschaft

Search
Browse
Statistics
Feeds

Automated reconstruction of whole-embryo cell lineages by learning from sparse annotations

[img]
Preview
PDF (Preprint) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
7MB
Item Type:Preprint
Title:Automated reconstruction of whole-embryo cell lineages by learning from sparse annotations
Creators Name:Malin-Mayor, C. and Hirsch, P. and Guignard, L. and McDole, K. and Wan, Y. and Lemon, W.C. and Keller, P.J. and Preibisch, S. and Funke, J.
Abstract:We present a method for automated nucleus identification and tracking in time-lapse microscopy recordings of entire developing embryos. Our method combines deep learning and global optimization to enable complete lineage reconstruction from sparse point annotations, and uses parallelization to process multi-terabyte light-sheet recordings, which we demonstrate on three common model organisms: mouse, zebrafish, Drosophila. On the most difficult dataset (mouse), our method correctly reconstructs 75.8% of cell lineages spanning 1 hour, compared to 31.8% for the previous state of the art, thus enabling biologists to determine where and when cell fate decisions are made in developing embryos, tissues, and organs.
Keywords:Animals, Drosophila, Mice, Zebrafish
Source:bioRxiv
Publisher:Cold Spring Harbor Laboratory Press
Article Number:2021.07.28.454016
Date:29 July 2021
Official Publication:https://doi.org/10.1101/2021.07.28.454016

Repository Staff Only: item control page

Downloads

Downloads per month over past year

Open Access
MDC Library