November 21, 2018 — Clarius Mobile Health will announce a new collective intelligence ultrasound platform at this year's Radiological Society of North America (RSNA) annual meeting, Nov. 25-30, 2018, in Chicago. The Clarius AI (artificial intelligence) solution focuses on data and image quality, ease of data collection, and a collaborative platform for both physicians and researchers to label and augment acquired images.
"One of the most challenging aspects of AI in healthcare is the ability to capture quality data that focuses on specific clinical needs," said Reza Zahiri, Ph.D., director of innovation at Clarius. He said the Clarius AI platform combined with their ultrasound scanners makes it easy to acquire and label large amounts of data.
The labeled data, which are created by medical experts, can then be fed into various AI frameworks such as TensorFlow or PyTorch for training. The trained models would eventually be deployed as clinical solutions for the Clarius app and Clarius Cloud and made available to medical experts around the world.
Compared to other imaging modalities, ultrasound has the advantage of being real-time. However, it is challenging to run images through trained algorithms at high frame rates. Clarius has leveraged and developed key technologies to run AI algorithms in real-time, where users will be able to simply download an updated app and get access to new AI features.
Zahiri said the Clarius Cloud is compliant with the Healthcare Insurance Portability and Accountability Act (HIPAA), with built-in security and scrubbing techniques from the ground up. This allows data to be automatically anonymized when being accessed for labeling and algorithm training. Clarius also follows the HITRUST CSF framework for regulatory compliance and risk management.
The Clarius AI platform will be available to any clinical research group or medical professional interested in developing their own AI tools.
For more information: www.clarius.com
