Sunday, December 1 | 10:50 a.m.-11:00 a.m. | SSC13-03 | Room S503AB
Synthesized 2D mammography isn't ready to be used as standalone technology when it comes to finding breast masses, according to research that will be presented Sunday morning.Presenter Liesbeth Vancoillie of Catholic University of Leuven in Belgium will share findings from a study that compared the detectability of masses on digital mammography, digital breast tomosynthesis (DBT), and synthesized 2D mammography for five vendors using a 3D phantom.
The study included the following systems:
- Fujifilm Medical Systems's Amulet Innovality ST
- GE Healthcare's Senographe Pristina
- Hologic's Selenia Dimensions
- Internazionale Medico Scientifica's (IMS) Giotto Class
- Siemens Healthineers' Mammomat Revelation
The researchers found that for the systems by GE, IMS, and Siemen, DBT performed significantly better than synthesized mammography. For Fuji's and Hologic's systems, they found no significant difference between DBT and synthesized mammography.
Detection of mass-like lesions was higher in DBT compared with digital mammography and synthesized mammography, except for Fuji and Hologic, for which synthesized mammography was not different from DBT, the team concluded.
For most vendors, synthesized mammography, "in its current stage of development, cannot be recommended as a standalone modality if equal mass detectability as in DBT is required," the researchers noted.












![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=112&q=70&w=112)






