Koios DS is a web-based AI software that helps trained physicians analyze ultrasound images of breast lesions and thyroid nodules suspicious for cancer. It automatically selects regions of interest, classifies lesions using standardized lexicons like BI-RADS and TI-RADS, provides cancer risk assessments, and generates structured reports to aid in clinical decision-making, improving diagnostic accuracy and reducing variability.
Koios DS is an AI/ML-based CADx software intended as an adjunct to diagnostic ultrasound examinations of lesions or nodules suspicious for breast or thyroid cancer.
Koios DS is a web-based software that processes user-selected Regions of Interest from breast or thyroid ultrasound DICOM images using AI engines. It automatically classifies lesions according to standard lexicons (BI-RADS for breast, TI-RADS and ATA for thyroid), provides cancer risk assessments, supports smart ROI selection tools, image viewing, and exports structured reports to PACS or third-party software.
Clinical and bench testing demonstrated that Koios DS improves reader performance for classification of breast lesions and thyroid nodules suspicious for cancer compared to unassisted ultrasound reading. The breast engine showed AUC improvement from 0.882 to 0.929 and maintained robustness in additional datasets. The thyroid engine significantly improved AUC by 0.083 overall and 0.074 in US-only cases, with increased sensitivity and specificity for biopsy and follow-up recommendations. Inter-reader variability decreased and interpretation time improved with Koios DS.
No predicate devices specified
Submission
8/18/2021
FDA Approval
12/16/2021
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.