A general algorithm for consensus 3D cell segmentation from 2D segmented stacks.

Autor: Zhou FY; Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA.; Cecil H. & Ida Green Center for System Biology, University of Texas Southwestern Medical Center, Dallas, TX, USA., Yapp C; Laboratory of Systems Pharmacology, Department of Systems Biology, Harvard Medical School, Boston, MA, 02115, USA.; Ludwig Center at Harvard, Harvard Medical School, Boston, MA, 02115, USA., Shang Z; Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA., Daetwyler S; Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA.; Cecil H. & Ida Green Center for System Biology, University of Texas Southwestern Medical Center, Dallas, TX, USA., Marin Z; Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA.; Cecil H. & Ida Green Center for System Biology, University of Texas Southwestern Medical Center, Dallas, TX, USA., Islam MT; Children's Research Institute and Department of Pediatrics, Howard Hughes Medical Institute, University of Texas Southwestern Medical Center, Dallas, TX, USA., Nanes B; Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA.; Cecil H. & Ida Green Center for System Biology, University of Texas Southwestern Medical Center, Dallas, TX, USA., Jenkins E; Kennedy Institute of Rheumatology, University of Oxford, OX3 7FY UK., Gihana GM; Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA.; Cecil H. & Ida Green Center for System Biology, University of Texas Southwestern Medical Center, Dallas, TX, USA., Chang BJ; Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA.; Cecil H. & Ida Green Center for System Biology, University of Texas Southwestern Medical Center, Dallas, TX, USA., Weems A; Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA.; Cecil H. & Ida Green Center for System Biology, University of Texas Southwestern Medical Center, Dallas, TX, USA., Dustin M; Kennedy Institute of Rheumatology, University of Oxford, OX3 7FY UK., Morrison S; Children's Research Institute and Department of Pediatrics, Howard Hughes Medical Institute, University of Texas Southwestern Medical Center, Dallas, TX, USA., Fiolka R; Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA.; Cecil H. & Ida Green Center for System Biology, University of Texas Southwestern Medical Center, Dallas, TX, USA., Dean K; Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA.; Cecil H. & Ida Green Center for System Biology, University of Texas Southwestern Medical Center, Dallas, TX, USA., Jamieson A; Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA., Sorger PK; Laboratory of Systems Pharmacology, Department of Systems Biology, Harvard Medical School, Boston, MA, 02115, USA.; Ludwig Center at Harvard, Harvard Medical School, Boston, MA, 02115, USA.; Department of Systems Biology, Harvard Medical School, 200 Longwood Avenue, Boston, MA 02115, USA., Danuser G; Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA.; Cecil H. & Ida Green Center for System Biology, University of Texas Southwestern Medical Center, Dallas, TX, USA.
Jazyk: angličtina
Zdroj: BioRxiv : the preprint server for biology [bioRxiv] 2024 May 06. Date of Electronic Publication: 2024 May 06.
DOI: 10.1101/2024.05.03.592249
Abstrakt: Cell segmentation is the fundamental task. Only by segmenting, can we define the quantitative spatial unit for collecting measurements to draw biological conclusions. Deep learning has revolutionized 2D cell segmentation, enabling generalized solutions across cell types and imaging modalities. This has been driven by the ease of scaling up image acquisition, annotation and computation. However 3D cell segmentation, which requires dense annotation of 2D slices still poses significant challenges. Labelling every cell in every 2D slice is prohibitive. Moreover it is ambiguous, necessitating cross-referencing with other orthoviews. Lastly, there is limited ability to unambiguously record and visualize 1000's of annotated cells. Here we develop a theory and toolbox, u-Segment3D for 2D-to-3D segmentation, compatible with any 2D segmentation method. Given optimal 2D segmentations, u-Segment3D generates the optimal 3D segmentation without data training, as demonstrated on 11 real life datasets, >70,000 cells, spanning single cells, cell aggregates and tissue.
Databáze: MEDLINE