A deep-learning, cancer detection software built on artificial intelligence (AI) called ProFound AI received clearance by the U.S. Food and Drug Administration (FDA) for commercial sales and clinical use in the United States. The announcement was made in a news release from iCAD, Inc., a global medical technology company that developed the software for digital breast tomosynthesis.
The FDA clearance is based on clinical results from a large reader study. The research was performed with 24 radiologists who read 260 tomosynthesis cases both with and without the AI technology. The findings showed increased cancer detection rates, reduced false-positive rates and patient recalls, and a significant decrease in interpretation times. The technology showed an improvement in cancer detection rates by an average of 8% and decreased unnecessary patient recall rates by an average of 7%. The AI is trained to detect malignant soft-tissue densities and calcifications. It also provides radiologists with scoring information representing the likelihood that a detection or case is malignant based on the large data set of clinical images used to train the algorithm.
According to the news release, in addition to improving clinical performance related to breast cancer detection and false-positive rates, study results showed that the AI technology can reduce radiologists’ reading time by more than 50% on average. ■