Clear-sighted neural network counts corneal cells

Our work on combining GDOCM and artificial intelligence for automated, unbiased estimation of corneal endothelial cell density was featured by SPIE.

Clear-sighted neural network counts corneal cells

The microscope uses a combination of optical coherence tomography, a liquid lens, and a microelectromechanical system mirror to provide beautifully sharp corneal images that help technicians assess the quality of the donated cornea. When combined with a neural network, automated cell counting prior to corneal translplant may be possible.