Few-shot Deep Learning for Phase-Amplitude Aberration Correction in Transcranial Focused Ultrasound
Using AI to fix how ultrasound beams scatter through skulls in seconds
Researchers developed an AI system that corrects distortions in focused ultrasound beams passing through the skull, which normally scatter and miss their targets. The system learned from diverse skull shapes and adapted to new patients with just ten data points, achieving accuracy within half a millimeter while running 2,500 times faster than conventional physics simulations.
Focused ultrasound is used to treat brain tumors, Parkinson's disease, and chronic pain without surgery, but skull distortions currently limit when and how well it works. This speedup transforms treatment planning from hours to seconds, making real-time beam adjustment possible during procedures and expanding which patients can safely receive the therapy.