Automated characterisation of microglia in ageing mice using image processing and supervised machine learning
Soyoung Choi1, Daniel Hill1, Li Guo1
1UCL Institute of Ophthalmology, London, EC1V 9EL, UK.
Abstract:
The resident macrophages of the central nervous system, microglia, are becoming increasingly implicated as active participants in neuropathology and ageing. Their diverse and changeable morphology is tightly linked with functions they perform, enabling assessment of their activity through image analysis. To better understand the contributions of microglia in health, senescence, and disease, it is necessary to measure morphology with both speed and reliability. A machine learning approach was developed to facilitate automatic classification of images of retinal microglial cells as one of five morphotypes, using a support vector machine (SVM). The area under the receiver operating characteristic curve for this SVM was between 0.99 and 1, indicating strong performance. The densities of the different microglial morphologies were automatically assessed (using the SVM) within wholemount retinal images. Retinas used in the study were sourced from 28 healthy C57/BL6 mice split over three age points (2, 6, and 28-months). The prevalence of 'activated' microglial morphology was significantly higher at 6- and 28-months compared to 2-months (p < .05 and p < .01 respectively), and 'rod' significantly higher at 6-months than 28-months (p < 0.01). The results of the present study propose a robust cell classification SVM, and further evidence of the dynamic role microglia play in ageing.
Insights
Microglia, the immune cells of the brain, change shape with age. This study developed a machine learning tool to automatically classify microglial morphology, revealing significant age-related changes in their activation states.
Area of Science:
- Neuroscience
- Immunology
- Computational Biology
Background:
- Microglia, the resident macrophages of the central nervous system, are increasingly recognized for their roles in neuropathology and aging.
- Microglial morphology is closely linked to their function, making it a key indicator of their activity.
- Accurate and efficient methods are needed to quantify microglial morphology for research into health, senescence, and disease.
Purpose of the Study:
- To develop and validate a machine learning model for the automatic classification of microglial morphology.
- To assess age-related changes in microglial morphology in the mouse retina.
Main Methods:
- A support vector machine (SVM) machine learning model was trained to classify retinal microglial cells into five morphotypes.
- The SVM model achieved high performance with an area under the receiver operating characteristic curve between 0.99 and 1.
- The densities of different microglial morphologies were automatically quantified in wholemount retinal images from mice aged 2, 6, and 28 months.
Main Results:
- The prevalence of 'activated' microglial morphology significantly increased with age (6 and 28 months vs. 2 months).
- A 'rod' morphology was significantly more prevalent at 6 months compared to 28 months.
- The study demonstrated the robust performance of the SVM for cell classification and provided evidence for dynamic microglial changes during aging.
Conclusions:
- A reliable machine learning-based SVM classifier for microglial morphology was developed.
- Significant age-dependent alterations in microglial morphology were observed in the mouse retina.
- These findings highlight the dynamic involvement of microglia in the aging process.
