A deep learning-based method of acoustic holographic lens generation for transcranial focused ultrasound

Acoustic holographic lenses provide the potential for transcranial focusing because they enable one to accurately and economically overcome distortion caused by the skull on ultrasonic waves. However, challenges remain in the design of acoustic holographic lenses for transcranial focusing. The time inversion method, which is the standard method for generating acoustic holographic lenses for transcranial focusing, is laborious. To overcome this limitation, we propose a U-Net-based transcranial focusing method that can effectively produce acoustic holographic lenses. The simulation results demonstrate that compared to traditional time-reversal methods, the proposed U-net-based approach can produce acoustic holographic lenses for transcranial focusing hundreds of times faster with comparable reconstruction quality. The experimental results show that the performance of the acoustic holograms produced by this methodology is comparable to that of the holograms produced by the traditional time-reversal method. However, the holograms are generated at a pace that is faster by a factor of more than 4000. The results demonstrate that the technique can quickly and accurately produce acoustic holographic lenses for transcranial focusing, opening the door to potential real-time transcranial focusing applications based on these lenses.