NYU researchers developed an AI model using longitudinal 3D mammograms that outperforms single-scan and 2D-based tools in predicting 5-year breast cancer risk.
Key Details
- 1NYU-DRP analyzes multiple years of 3D mammograms (longitudinal DBT) for risk prediction.
- 2Study included 313,531 yearly scans from 161,165 women (2016-2020).
- 3NYU-DRP correctly ranked high-risk cases 72% of the time, compared to 70% (single DBT) and 68% (AI 2D).
- 4Outperformed the Tyrer-Cuzick risk model (67% vs. 56% accuracy for 5-year high-risk predictions).
- 5Dense breast tissue alone did not predict future risk as reliably as the AI model.
- 6Study funded by NSF, NIH, and several breast cancer foundations.
Why It Matters
Improved personalized risk stratification with AI could enable more tailored breast cancer screening protocols, reducing over-screening and improving detection for high-risk women. The adoption of longitudinal 3D mammogram analysis signals an advancement in imaging AI's capability for real-world risk prediction.
Source
EurekAlert
Related News
•EurekAlert
AI Framework Adapts Smartphone Audio for Pediatric Lung Sound Screening
Researchers developed a domain-adaptive deep learning model enabling smartphones to detect abnormal lung sounds in children for remote screening.
•EurekAlert
HKU Launches Centre for Health AI Research and Translation
The University of Hong Kong has established the Centre for Health AI Research and Translation (CHART) to drive trustworthy, patient-centered AI innovation in healthcare.
•EurekAlert
Holographic Neural Network Achieves Multi-Task AI via Light-Based Computing
Researchers have developed a holographic neural network using optics to perform multiple AI classification tasks simultaneously without hardware reconfiguration.