Breast

DeepHealth, a RadNet AI subsidiary, is a leading developer of artificial intelligence for mammography interpretation. DeepHealth’s flagship product, Saige-Dx™, automatically identifies suspicious lesions in mammograms and assigns a suspicion level to each finding and to the entire case.

Saige-Dx helps radiologists interpret mammograms more accurately and efficiently.

• FDA-cleared technology.

• Support for both 2D full-field digital mammograms and 3D digital breast tomosynthesis.

• High performance across different breast densities and lesion types.

• Automatic prioritization of cases with a high likelihood of cancer, enabling faster reads.

• Algorithms trained on more than a million images, 100,000 cases, and 8,000 biopsy-proven cancers, as well as on diverse populations.

“In medicine, the ability to see and detect disease with more certainty is a game-changer, driving better patient outcomes. We are using AI to detect breast cancers that the human eye might not notice. In my experience, the addition of these proven, FDA-cleared algorithms has allowed us to detect hundreds of cancers that otherwise would not have been found at the time of screening.”

Jacqueline Holt, M.D.
Medical Director, Delaware Imaging Network

Enhanced Breast Cancer Detection

Saige-Dx is the central component of RadNet’s Enhanced Breast Cancer Detection service, which is designed for women who want an improved level of accuracy in breast cancer detection during their annual screening.

Demonstrated Performance Gains

In a study to validate the efficacy of Saige-Dx, 18 radiologists read 240 mammograms twice—once with the aid of the technology and once without. All 18 radiologists showed improved performance when using Saige-Dx.¹

¹ Data from the multi-reader multi-center reader study conducted to evaluate the performance of MQSA qualified radiologists with and without the aid of Saige-Dx™. Study results available in Saige-Dx™ Instructions for Use.