Proprietary processing algorithms present challenges

December 1, 2007
Margarita Zuley, MD
Margarita Zuley, MD

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.