Development and piloting of automation for analysis of the blood-brain barrier using deep neural networks

We will develop a framework for the automated detection of complex-shaped cells, utilising machine-learning algorithms applied to digitised whole slide images of tissue sections. These supervised deep learning models will focus on specific cellular properties, including morphological features and the cellular arrangements within the intricate tissue microarchitecture. Due to the anatomical diversity and the morphological variability of astrocytes, the detection and quantification of such complexities is challenging. We will compare the effectiveness of the developed models and their potential benefits with those of traditional analysis methods, advancing digital pathology approaches and deepening our understanding of astrocyte dynamics in the context of CNS disorders.