What is it about?
To understand neuronal survival after a hypoxic-ischemic (HI) attack on the neonatal brain, it is imperative to distinguish between the healthy and dying neurons/cells in histological brain images of HI sheep models. This paper took the first step towards the automated classification of healthy and dying cells in HI images. The paper proposes a novel machine-learning method for that purpose.
Featured Image
Photo by Hal Gatewood on Unsplash
Why is it important?
The histological analysis of neuronal survival after imposing a HI attack on animal models is a manual assessment process. It is a time-consuming task that is very much subjective to human perspectives, introducing inter-rater variability in the assessment. Thus, the need to automate the process that will bring much-needed transparency and accuracy to it.
Perspectives
I hope this article encourages researchers to investigate automating the manual identification and quantification process of neuronal survival after an HI attack on the neonatal brain. It is a much-needed but often overlooked part of the research on the possible treatments after the HI attack on the neonatal brain. I am glad to be part of this project.
Saheli Bhattacharya
University of Auckland
Read the Original
This page is a summary of: Multi-layer perceptron classification & quantification of neuronal survival in hypoxic-ischemic brain image slices using a novel gradient direction, grey level co-occurrence matrix image training, PLoS ONE, December 2022, PLOS,
DOI: 10.1371/journal.pone.0278874.
You can read the full text:
Contributors
The following have contributed to this page
