A comparison of machine learning approaches for the quantification of microglial cells in the brain of mice, rats and non-human primates

Authors

Danish M. Anwer, Behavioural Neuroscience Laboratory, Department of Experimental Medical Sciences, Lund University Lund, Sweden.
Francesco Gubinelli, Behavioural Neuroscience Laboratory, Department of Experimental Medical Sciences, Lund University Lund, Sweden.
Yunus A. Kurt, Behavioural Neuroscience Laboratory, Department of Experimental Medical Sciences, Lund University Lund, Sweden.
Livija Sarauskyte, Behavioural Neuroscience Laboratory, Department of Experimental Medical Sciences, Lund University Lund, Sweden.
Febe Jacobs, Behavioural Neuroscience Laboratory, Department of Experimental Medical Sciences, Lund University Lund, Sweden.
Chiara Venuti, Behavioural Neuroscience Laboratory, Department of Experimental Medical Sciences, Lund University Lund, Sweden.
Ivette M. Sandoval, Barrow Neurological Institute, Parkinson's Disease Research Unit, Department of Translational Neuroscience, Phoenix, Arizona, United States of America.
Yiyi Yang, Experimental Neuroinflammation Laboratory, Department of Experimental Medical Sciences, Lund University, Lund, Sweden.
Jennifer Stancati, Translational Neuroscience, College of Human Medicine, Michigan State University, Grand Rapids, MI, United States of America.
Martina Mazzocchi, Brain Development and Repair Group, Department of Anatomy and Neuroscience University College Cork, Cork, Ireland.
Edoardo Brandi, Neural Plasticity and Repair, Department of Experimental Medical Sciences, Lund University, Lund, Sweden.
Gerard O'Keeffe, Brain Development and Repair Group, Department of Anatomy and Neuroscience University College Cork, Cork, Ireland.
Kathy Steece-Collier, Translational Neuroscience, College of Human Medicine, Michigan State University, Grand Rapids, MI, United States of America.
Jia-Yi Li, Neural Plasticity and Repair, Department of Experimental Medical Sciences, Lund University, Lund, Sweden.
Tomas Deierborg, Experimental Neuroinflammation Laboratory, Department of Experimental Medical Sciences, Lund University, Lund, Sweden.
Fredric P. Manfredsson, Barrow Neurological Institute, Parkinson's Disease Research Unit, Department of Translational Neuroscience, Phoenix, Arizona, United States of America.Follow
Marcus Davidsson, Behavioural Neuroscience Laboratory, Department of Experimental Medical Sciences, Lund University Lund, Sweden.
Andreas Heuer, Behavioural Neuroscience Laboratory, Department of Experimental Medical Sciences, Lund University Lund, Sweden.

Document Type

Article

Abstract

Microglial cells are brain-specific macrophages that swiftly react to disruptive events in the brain. Microglial activation leads to specific modifications, including proliferation, morphological changes, migration to the site of insult, and changes in gene expression profiles. A change in inflammatory status has been linked to many neurodegenerative diseases such as Parkinson's disease and Alzheimer's disease. For this reason, the investigation and quantification of microglial cells is essential for better understanding their role in disease progression as well as for evaluating the cytocompatibility of novel therapeutic approaches for such conditions. In the following study we implemented a machine learning-based approach for the fast and automatized quantification of microglial cells; this tool was compared with manual quantification (ground truth), and with alternative free-ware such as the threshold-based ImageJ and the machine learning-based Ilastik. We first trained the algorithms on brain tissue obtained from rats and non-human primate immunohistochemically labelled for microglia. Subsequently we validated the accuracy of the trained algorithms in a preclinical rodent model of Parkinson's disease and demonstrated the robustness of the algorithms on tissue obtained from mice, as well as from images provided by three collaborating laboratories. Our results indicate that machine learning algorithms can detect and quantify microglial cells in all the three mammalian species in a precise manner, equipotent to the one observed following manual counting. Using this tool, we were able to detect and quantify small changes between the hemispheres, suggesting the power and reliability of the algorithm. Such a tool will be very useful for investigation of microglial response in disease development, as well as in the investigation of compatible novel therapeutics targeting the brain. As all network weights and labelled training data are made available, together with our step-by-step user guide, we anticipate that many laboratories will implement machine learning-based quantification of microglial cells in their research.

Medical Subject Headings

Mice; Rats; Animals; Microglia (metabolism); Parkinson Disease (metabolism); Reproducibility of Results; Brain; Primates; Machine Learning; Mammals

Publication Date

1-1-2023

Publication Title

PloS one

E-ISSN

1932-6203

Volume

18

Issue

5

First Page

e0284480

PubMed ID

37126506

Digital Object Identifier (DOI)

10.1371/journal.pone.0284480

Recommended Citation

Anwer, Danish M.; Gubinelli, Francesco; Kurt, Yunus A.; Sarauskyte, Livija; Jacobs, Febe; Venuti, Chiara; Sandoval, Ivette M.; Yang, Yiyi; Stancati, Jennifer; Mazzocchi, Martina; Brandi, Edoardo; O'Keeffe, Gerard; Steece-Collier, Kathy; Li, Jia-Yi; Deierborg, Tomas; Manfredsson, Fredric P.; Davidsson, Marcus; and Heuer, Andreas, "A comparison of machine learning approaches for the quantification of microglial cells in the brain of mice, rats and non-human primates" (2023). Translational Neuroscience. 2232.
https://scholar.barrowneuro.org/neurobiology/2232