Synthetic mammography performed equally as well to digital mammography with less radiation exposure.
Synthetic digital mammography images could be the next step in breast imaging, taking the place of digital mammography and improving patient experience, according to newly released study.
In a Sept. 23 article published in the American Journal of Roentgenology, a team from Canada shared the results of a review study that showed synthetic images re-produced from digital breast tomosynthesis scans have the same level of accuracy as those captured with traditional digital mammography.
Digital breast tomosynthesis has gained traction in recent years thanks to the growing body of evidence around its reduced recall and improved cancer detection rates. However, its use with traditional digital mammography also increases radiation exposure, said lead study author Peri Abdullah, Ph.D. Incorporating synthetic images instead could eliminate that added dose, Abdullah's team said.
“Reconstructing a synthetic image does not require additional radiation exposure beyond that required for digital breast tomosynthesis, which is not the case if digital mammography also has to be performed for the same patient,” the team wrote. “This is of concern when considering the risk of radiation-induced cancers, which may be higher with increased cumulative radiation doses.”
Related Content: Pairing DBT with Automated Breast Density Measurements Leads to Fewer Recalls
To determine the accuracy of synthetic images, Abdullah’s team analyzed 13 existing studies that examined patients who received synthesized 2D mammograms and conventional digital mammograms with or without additional digital breast tomosynthesis. All total, the studies included 201,304 patients.
According to their review, the team determined there was no significant difference in sensitivity or specificity between digital mammography and synthetic mammography either as stand-alone imaging techniques or in concert with digital breast tomosynthesis. And, they found, adjusting for bias, design, or reference standard did not make a difference.
In an accompanying editorial, Reni Butler, M.D., a breast imaging specialist and associate professor of radiology and biomedical imaging at Yale University School of Medicine, said these results indicate that using one scan for both 3D and 2D imaging is a possibility.
“This study supports utilization of digital breast tomosynthesis as a single acquisition-examination,” she said, “without a second radiation exposure to obtain a conventional 2D digital mammography.”
According to Abdullah’s team, the existing research indicates radiation dose drops by approximately half when providers use synthetic 2D images with digital breast tomosynthesis rather than digital mammography. This finding, they said, bolsters greater use of synthetic images.
But, the use of synthetic images still faces challenges, said Yale’s Butler. Some providers are still concerned that these re-produced images might have decreased sensitivity for fine micro-calcifications, subtle masses, and artificial pseudo-calcifications. But, some changes to daily practice, such as continuing to use traditional digital mammography for baseline screenings or capturing magnification views of micro-calcifications, could improve providers’ comfort level with using synthetic images.
“With minor adjustments to imaging protocols and reading patterns, these justifiable concerns can be largely overcome,” Butler said. “With these adaptations, the learning curve for incorporating synthetic mammography into clinical practice and achieving an acceptable level of comfort with it can be reasonably short.”
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.