AI makes focused ultrasound therapy more effective, study finds

Credit: Unsplash+

Researchers led by Dr. Kim Hyungmin at the Korea Institute of Science and Technology (KIST) have made a significant advancement in the field of non-invasive focused ultrasound therapy.

Their groundbreaking research, published in the journal NeuroImage, has developed a real-time acoustic simulation technology using generative AI.

This technology is poised to transform the treatment of various brain diseases, such as depression and Alzheimer’s disease, by enhancing the precision and safety of focused ultrasound treatments.

Focused ultrasound is a non-invasive method that targets a few millimeters of the brain, including its deeper regions, to treat neurological disorders without needing to open the skull.

Its appeal lies in minimizing damage to surrounding healthy tissues and reducing side effects like complications and infections.

However, its application has been limited due to challenges in adjusting for the distortion of ultrasound waves caused by the varying shapes of patients’ skulls.

Previous methods relied on navigation systems based on medical images taken before treatment. These systems provide relative positioning information but fall short in accounting for real-time distortions caused by the skull.

While various simulation techniques attempted to compensate for this, their extensive computational time hindered practical clinical application.

Dr. Kim’s team has overcome these challenges by developing a real-time focused ultrasound simulation technology through an AI model based on a generative adversarial neural network (GAN).

This deep learning model, commonly used for image generation in medicine, has significantly sped up the process. The update time for three-dimensional simulation information is now reduced from 14 seconds to just 0.1 second.

Remarkably, this acceleration in processing time does not compromise accuracy, with errors in acoustic pressure and focal position well within acceptable ranges.

This technological breakthrough extends beyond just speed and accuracy. The research team also developed a medical image-based navigation system to rapidly integrate this technology into clinical practice.

This system can provide real-time acoustic simulations at a rate of 5 Hz, based on the position of the ultrasound transducer. It enables the prediction of ultrasound energy and focus positions within the skull in real time during therapy.

Previously, the ultrasound transducer had to be positioned precisely in a pre-planned location due to long calculation times. However, with this new simulation-guided navigation system, adjustments to the ultrasound focus can be made based on real-time acoustic simulations.

This capability is crucial for responding swiftly to unforeseen situations during treatment, thereby improving the accuracy of focused ultrasound therapy and ensuring patient safety.

Dr. Kim Hyungmin emphasizes the significance of this research in enhancing the accuracy and safety of focused ultrasound treatments for brain diseases.

The team plans further validations with diverse ultrasound sonication environments, including multi-array ultrasound transducers, paving the way for broader clinical applications.

This innovation marks a major step forward in providing safer and more effective treatment options for patients with neurological disorders.

If you care about wellness, please read studies about how ultra-processed foods and red meat influence your longevity, and why seafood may boost healthy aging.

For more information about wellness, please see recent studies that olive oil may help you live longer, and vitamin D could help lower the risk of autoimmune diseases.

The research findings can be found in NeuroImage.

Copyright © 2023 Knowridge Science Report. All rights reserved.