Researchers have developed a new AI model that could be a game-changer in the treatment of blindness and vision loss, sharing their findings in Frontiers in Cellular Neuroscience.
The team found that convolutional neural networks (CNNs) can be trained to recognize, differentiate and predict retinal tissues during the process of tissue differentiation in stem cell-derived organoids. This could help scientists grow retinal tissue, a key step in developing new drugs and treatments focused on cell replacement.
“The human retina has a very limited capacity for regeneration,” study co-author Pavel Volchkov, a geneticist at the Moscow Institute of Physics and Technology, said in a statement. “This means that any progressive loss of neurons—for example, in glaucoma—inevitably leads to complete loss of vision. And there is nothing a physician can recommend, short of getting a head start on learning Braille. Our research takes biomedicine a step closer to creating a cellular therapy for retinal diseases that would not only halt the progression but reverse vision loss.”
The CNN was trained on 750 images, with 400 additional images being set aside for validation and testing, and its final accuracy was 84%.
There is potential, the specialists wrote, that this breakthrough could lead to the growth of other human artificial organs as well.
The full Frontiers in Cellular Neuroscience study is available here.