McLabel: A Local Thresholding Tool for Efficient Semi-automatic Labelling of Cells in Fluorescence Microscopy

Utz J, Schlereth M, Qiu J, Thies M, Wagner F, Brahim OB, Gu M, Uderhardt S, Breininger K (2023)

Publication Type: Conference contribution

Publication year: 2023

Journal

Informatik aktuell Gesellschaft für Informatik (GI)

Publisher: Springer Science and Business Media Deutschland GmbH

Pages Range: 82-87

Conference Proceedings Title: Informatik aktuell

Event location: Braunschweig, DEU

ISBN: 9783658416560

DOI: 10.1007/978-3-658-41657-7_20

Abstract

In this work, we present a semi-automatic labelling tool for the annotation of complex cellular structures such as macrophages in fluorescence microscopy images. We present McLabel, a napari plugin that allows users to label structures of interest by simply scribbling outlines around the area of interest, using the triangle thresholding method with post-processing to identify the desired structure. Additionally, manual adaption of the threshold allows for quick and fine-grained local correction of the segmentation. The tool is evaluated in a user study with five experts, who annotated images both with and without the tool. The results show that variability in annotations between experts is reduced when the labelling tool is used and annotation time is reduced by a factor of five on average¹.

Authors with CRIS profile

Jonas Utz Juniorprofessur für Artificial Intelligence in Medical Imaging Maja Schlereth Juniorprofessur für Artificial Intelligence in Medical Imaging Jingna Qiu Juniorprofessur für Artificial Intelligence in Medical Imaging Mareike Thies Lehrstuhl für Informatik 5 (Mustererkennung) Fabian Wagner Lehrstuhl für Informatik 5 (Mustererkennung) Mingxuan Gu Lehrstuhl für Informatik 5 (Mustererkennung) Stefan Uderhardt Department of Medicine 3 – Rheumatology and Immunology Katharina Breininger Juniorprofessur für Artificial Intelligence in Medical Imaging

How to cite

APA:

Utz, J., Schlereth, M., Qiu, J., Thies, M., Wagner, F., Brahim, O.B.,... Breininger, K. (2023). McLabel: A Local Thresholding Tool for Efficient Semi-automatic Labelling of Cells in Fluorescence Microscopy. In Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus Maier-Hein, Christoph Palm, Thomas Tolxdorff (Eds.), Informatik aktuell (pp. 82-87). Braunschweig, DEU: Springer Science and Business Media Deutschland GmbH.

MLA:

Utz, Jonas, et al. "McLabel: A Local Thresholding Tool for Efficient Semi-automatic Labelling of Cells in Fluorescence Microscopy." Proceedings of the Bildverarbeitung für die Medizin Workshop, BVM 2023, Braunschweig, DEU Ed. Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus Maier-Hein, Christoph Palm, Thomas Tolxdorff, Springer Science and Business Media Deutschland GmbH, 2023. 82-87.

BibTeX: Download