Proprietary processing algorithms present challenges
Every mammogram is different, and every patient is her own control. Mammographers are watching for changes over time. But the digital age has brought with it some challenges. Because each digital mammography vendor uses proprietary processing algorithms, it may be hard to distinguish pathology from actual differences in image quality that can occur when images are scaled up. Everything scales differently.
Every mammogram is different, and every patient is her own control. Mammographers are watching for changes over time. But the digital age has brought with it some challenges. Because each digital mammography vendor uses proprietary processing algorithms, it may be hard to distinguish pathology from actual differences in image quality that can occur when images are scaled up. Everything scales differently.
For example, a nodule on a second-year mammogram might appear bigger than on the initial scan when it's scaled up. But each scan was taken on a different machine with different processing algorithms. Is the nodule actually bigger, or is it just scaled bigger?
I've looked at images from the same patient three years in a row, from three different units. And my question is, Does that mass or tissue look different because of processing algorithms, or has there been a real change?
Processing algorithms are the most variable aspects of digital mammography we face today. They improve image quality, no doubt, but they are vendor-specific and change every year when vendors introduce innovations.
AI-Initiated Recalls After Screening Mammography Demonstrate Higher PPV for Breast Cancer
March 18th 2025While recalls initiated by one of two reviewing radiologists after screening mammography were nearly 10 percent higher than recalls initiated by an AI software, the AI-initiated recalls had an 85 percent higher positive predictive value for breast cancer, according to a new study.
ECR Mammography Study: Pre-Op CEM Detects 34 Percent More Multifocal Masses than Mammography
February 28th 2025In addition to contrast-enhanced mammography (CEM) demonstrating over a 90 percent detection rate for multifocal masses, researchers found that no significant difference between histological measurements and CEM, according to study findings presented at the European Congress of Radiology.
Study: Mammography AI Leads to 29 Percent Increase in Breast Cancer Detection
February 5th 2025Use of the mammography AI software had a nearly equivalent false positive rate as unassisted radiologist interpretation and resulted in a 44 percent reduction in screen reading workload, according to findings from a randomized controlled trial involving over 105,000 women.
