In 2007, our engineers using radar technology and machine learning to help the U.S. Army catch bad guys figured out how to use that same technology to catch bad cancer cells. We have been hard at work for over 12 years experimenting, improving performance and developing software around the needs and workflow of interpreting physicians and technicians. In that time we have trained our proprietary algorithms on a dataset that now exceeds 500,000 ultrasound images of breast lesions all tied to pathology results or at least 1-year follow-up.

Koios DS Breast is the only FDA-cleared cancer diagnosis software using AI on breast ultrasound images, and works with the physician as an expert on-demand second opinion for classifying suspicious lesions and aligning to a BI-RADS category, while automatically prepopulating diagnostic reports. Koios DS is available directly on an ultrasound scanner and/or simply installed and connected to any PACS, and provides feedback useful for diagnosis and clinical decision making while streamlining workflow.