- AI
- Molecular Imaging
- CT
- X-Ray
- Ultrasound
- MRI
- Facility Management
- Mammography
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.
Mammography Study Suggests DBT-Based AI May Help Reduce Disparities with Breast Cancer Screening
December 13th 2024New research suggests that AI-powered assessment of digital breast tomosynthesis (DBT) for short-term breast cancer risk may help address racial disparities with detection and shortcomings of traditional mammography in women with dense breasts.
FDA Clears Updated AI Platform for Digital Breast Tomosynthesis
November 12th 2024Employing advanced deep learning convolutional neural networks, ProFound Detection Version 4.0 reportedly offers a 50 percent improvement in detecting cancer in dense breasts in comparison to the previous version of the software.
