The quantification of neurotoxicity contributes to a better understanding of the global scope of brain injury and aids qualitative histological examination. Although the process takes time, stereological techniques, including the use of an optical fractionator, offer an objective measurement of the neuronal damage. With the introduction of whole slide imaging (WSI) and digital image processing, neurotoxicity could now be quantified automatically, more quickly, and with less bias, enabling statistical comparisons. Simple digital picture analysis requires the manual labour of professionals, even though it can be automated to some extent. This limits the analysis of huge datasets and takes time. A deep learning artificial intelligence model combined with digital image analysis offers a viable substitute for laborious stereological and basic digital analysis. Deep learning algorithms could be trained to automatically recognise damaged or dead neurons. The works that show how deep learning is employed in brain region segmentation, toxicity detection, neuronal degeneration quantification, and area/volume estimation of degeneration have been the main emphasis of this paper.

Neurotoxicology, Artificial intelligence, Deeplearning, stereological techniques, WSI.