June 9, 2025 — A new independent, peer-reviewed study published in the journal Clinical Breast Cancer reinforces the impact of iCAD’s ProFound AI in clinical breast imaging, showing meaningful improvements in detection, diagnostic accuracy, and workflow efficiency for radiologists.
iCAD has developed ProFound AI to support radiologists with deep-learning tools that enhance the interpretation of 3D mammography, also known as digital breast tomosynthesis (DBT). This study underscores the real-world effectiveness of iCAD’s technology in advancing earlier and more accurate breast cancer detection, critical in an era of rising breast cancer rates, particularly among younger women.
Led by Dr. James Nepute of Indiana University, the study analyzed over 16,000 DBT cases and found that radiologists using ProFound AI identified 65% more cancers than those reading without AI support (cancer detection rate of 6.1 vs. 3.7 per 1,000). ProFound AI also proved especially effective in identifying invasive cancers.
Key findings include:
- Improved accuracy:
- Positive Predictive Value for abnormal interpretations (PPV1) doubled with AI: 8.8% vs. 4.2%
- PPV3 for biopsies increased to 57% vs. 32% without AI
- Fewer false positives:
- Abnormal interpretation rate dropped from 8.2% to 6.5%
- Specificity increased to 94% from 92%
These findings demonstrate how AI can reduce unnecessary callbacks, increase diagnostic confidence, and support more efficient workflows for radiologists.
The authors of the paper attribute the results to the use of deep learning models that flag suspicious findings while integrating seamlessly into radiologist workflows, making AI not just a research tool, but a clinical asset.
For more information, please visit www.icadmed.com.
June 12, 2026 
