Synthetic Skull CT

Synthetic skull CT generation uses artificial intelligence, specifically generative adversarial networks (GANs) and convolutional neural networks (CNNs), to create realistic computer-generated skull CT images from other readily available medical scans like MRI. This addresses the limitations of real CT scans, such as radiation exposure and data scarcity, while enabling the training of deep learning models for various applications. Current research focuses on improving the accuracy and realism of synthetic CTs, primarily for enhancing transcranial ultrasound and focused ultrasound therapies by providing accurate skull acoustic property estimations for treatment planning. This technology has the potential to significantly improve the efficiency and safety of neurosurgical procedures and related deep learning applications.

Papers