International researchers have used artificial intelligence (AI) to develop a model that could fundamentally transform the treatment of blindness and vision loss in the future.
The team trained an artificial neural network – that is, a computer algorithm that mimics the functioning of neurons in the human brain – to identify and predict differentiated cells in retinal tissue. The machine was able to recognise differentiated cells with 84 per cent accuracy, compared with 67 per cent achieved by humans.
“The human retina has a very limited capacity for regeneration,” said Pavel Volchkov of the Moscow Institute of Physics and Technology. “This means that any progressive loss of neurons – for example, in glaucoma – inevitably leads to complete loss of vision.” “We have taken a step closer to developing cell therapies for retinal diseases. Furthermore, the approach can be applied not only to other cell lines but also to other human artificial organs,” said co-author Evgenii Kegeles from the Schepens Eye Research Institute, USA.
References:
Moscow Institute of Physics and Technology – MIPT, Ivannikov Institute for System Programming, Schepens Eye Research Institute
Convolutional Neural Networks Can Predict Retinal Differentiation in Retinal Organoids
Front. Cell. Neurosci., 3 July 2020 |
https://doi.org/10.3389/fncel.2020.00171