Eye movements are typically recorded with eye-tracking sensory technology in which infrared light is projected into the retina, and then for measurement. Due to strong magnetic fields in MRI, such trackers, or cameras, need to be MRI-compatible. Existing cameras are expensive and are cumbersome to use. That’s why until now, eye-tracking has not been a widespread part of MRI examinations.
This may now change thanks to a new open-source ML model DeepMReye based on a CNN (convolutional neural network). To make eye tracking freely and widely available for MRI research, Mattias Nau, Markus Frey and Christian Doeller developed DeepMReye: a convolutional neural network that decodes gaze position from the MR-signal of the eyeballs.
This model is able to track eye movement when eyes are opened or closed- without using eye trackers during MRI. This model can be used for blind patients.
The model could be used by sleep researchers to study eye movements in different sleep stages. The software also has the potential for use by clinicians to diagnose disorders that manifest in changes in eye movement patterns.
Eye tracking is important to interpret brain activity. Decoded eye movements explain network-wide brain activity also in regions not associated with oculomotor function.
“Eyes are the window to the brain. This is because your eyes are direct extensions of your brain that sprout out during development. Then, we rely on our visual system to tell us where we are in space and what is around us. In order to map our world, we need the ability to move our eyes to see it. This requires a large amount of brain activity from many areas that are interconnected through brain circuits.” Dr.Nick
