RadNet touts results from largest real-world analysis of AI-powered breast cancer screening in US history
RadNet Inc. on Monday touted results from what it says is the largest real-world analysis of artificial intelligence-backed breast cancer screening in U.S. history.
Published in Nature Health, the study included mammograms from over 579,000 women treated across 109 imaging sites in California, Delaware, Maryland and New York. The analysis found that adding AI boosted the cancer detection rate by 21.6% compared to standard 3D mammo screening.
This while maintaining regular recall rates and increasing positive predictive value (the probability a person who receives a positive result has the disease) by 15%.
“Beyond the remarkable results, what sets this research apart is its scale, diversity and real-world applicability,” RadNet President and CEO Howard Berger, MD, said in an announcement about the results on Nov. 17. “There has never been a similar study of this size in the United States, much less one with such a diverse patient population, that examines the patient impact and efficacy of AI-assisted breast cancer screening.”
Researchers compared utilization of RadNet’s Enhanced Breast Cancer Detection (EBCD) program—which now charges an extra $40 to have AI read over mammograms—against the standard of care. Altogether, the study included nearly 209,000 women who received AI-backed breast imaging against another nearly 371,000 who received regular screenings. The findings come from the AI-Supported Safeguard Review Evaluation (ASSURE) study, launched to evaluate how artificial intelligence impacts imaging. RadNet also highlighted the inclusion of over 150,000 black women—a population that has faced 40% higher breast cancer mortality risk in the U.S.
Launched in 2023, EBCD combines FDA-cleared, computer-aided detection and diagnosis software with an AI safeguard review. The latter can trigger a second breast imaging expert’s analysis in the case of high-suspicion cases, RadNet noted. ASSURE also showed that the workflow underlying EBCD delivered a 22.7% boost in cancer detection rate compared to regular screening for women with dense breasts.
To avoid selection bias, the AI option was provided to all patients at no additional charge during the study period, noted Gregory Sorensen, MD, study co-author and RadNet’s chief science officer.
“Unlike many academically focused studies, these screenings took place at community imaging centers, where most women get their mammograms,” he said in the announcement. “These real-world findings demonstrate how AI can improve access to specialist-level care for women, no matter where they live,” Sorensen added later.
RadNet also previously presented findings from its EBCD program at the Radiological Society of North America’s annual meeting in 2024. The publicly traded company operates a total of over 400 outpatient imaging centers spread across eight states.
Marty Stempniak has covered healthcare since 2012, with his byline appearing in the American Hospital Association's member magazine, Modern Healthcare and McKnight's. Prior to that, he wrote about village government and local business for his hometown newspaper in Oak Park, Illinois. He won a Peter Lisagor and Gold EXCEL awards in 2017 for his coverage of the opioid epidemic.