Automated 3D cytoplasm segmentation in soft X-ray tomography

• Verfasst von: Aydogdu-Erozan, Ayse [VerfasserIn]
• Verfasst von: Lösel, Philipp [VerfasserIn]
• Verfasst von: Heuveline, Vincent [VerfasserIn]
• Verfasst von: Weinhardt, Venera [VerfasserIn]
• Titel: Automated 3D cytoplasm segmentation in soft X-ray tomography
• Verf.angabe: Ayse Erozan, Philipp D. Lösel, Vincent Heuveline, and Venera Weinhardt
• E-Jahr: 2024
• Jahr: 21 June 2024
• Umfang: 11 S.
• Illustrationen: Illustrationen
• Fussnoten: Online verfügbar: 29. April 2024, Artikelversion: 15. Mai 2024 ; Gesehen am 03.01.2025
• Titel Quelle: Enthalten in: iScience
• Ort Quelle: Amsterdam : Elsevier, 2018
• Jahr Quelle: 2024
• Band/Heft Quelle: 27(2024), 6 vom: Juni, Artikel-ID 109856, Seite 1-11
• ISSN Quelle: 2589-0042
• DOI: doi:10.1016/j.isci.2024.109856
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Artificial intelligence
• Sach-SW: Cell biology
• K10plus-PPN: 1913488721

Abstract

Cells’ structure is key to understanding cellular function, diagnostics, and therapy development. Soft X-ray tomography (SXT) is a unique tool to image cellular structure without fixation or labeling at high spatial resolution and throughput. Fast acquisition times increase demand for accelerated image analysis, like segmentation. Currently, segmenting cellular structures is done manually and is a major bottleneck in the SXT data analysis. This paper introduces ACSeg, an automated 3D cytoplasm segmentation model. ACSeg is generated using semi-automated labels and 3D U-Net and is trained on 43 SXT tomograms of immune T cells, rapidly converging to high-accuracy segmentation, therefore reducing time and labor. Furthermore, adding only 6 SXT tomograms of other cell types diversifies the model, showing potential for optimal experimental design. ACSeg successfully segmented unseen tomograms and is published on Biomedisa, enabling high-throughput analysis of cell volume and structure of cytoplasm in diverse cell types.