Nashua, New Hampshire-based iCad trained its next-generation AI solution using deep learning convolutional neural networks (CNN). It offers advancements in cancer detection and specificity, improving the identification of hard-to-find and aggressive cancers. The technology also reduces false positives and introduces a new option for clinicians to incorporate a prior exam into its analysis.

The latest version builds upon iCad’s previous DBT solutions. The first of those received FDA clearance in 2016. Version 4.0 now extends that by offering enhancements in detection and precision. iCad now offers the technology in the U.S. and expects to add more global and vendor-specific regulatory expansions in 2025.

Compared to the previous ProFound Detection version, this one provides a 22% overall improvement in detecting some of the most challenging and aggressive cancer subtypes, the company says. That includes a 50% improvement in identifying cancers within dense breast tissue.