Project title: Embedded AI for next generation biomedical optical imaging systems
PI: Martin Booth
Optical microscopes suffer from aberrations, which are optical distortions introduced by imperfect hardware and innate sample structures that can detrimentally affect image quality. Adaptive optics (AO) uses reconfigurable devices to correct aberrations, but such methods have limitations such as required prolonged exposures that cause sample photodamage. This work embeds neural network algorithms into the feedback control of the AO system, resulting in a structure orders of magnitude smaller in terms of trainable parameters than many commonly-used architectures.
