Screening mammography image readings by radiologists are influenced by individual technologists.
How radiologists interpret screening mammographies varies substantially by the technologist performing the examination, according to a study published in the journal Academic Radiology.
Researchers from the University of North Carolina in Chapel Hill undertook a retrospective cohort study to determine whether mammographic technologists have an effect on the radiologists' interpretative performance of screening mammography in community practice.
For the study, the researchers used information obtained from the Carolina Mammography register, including data from 372 radiologists and 356 mammographic technologists from 1994 to 2009, who performed 1,003,276 screening mammograms. Performance measures included recall rate, sensitivity, specificity, positive predictive value (PPV1), and cancer detection rate (CDR).
The findings showed that 343 of the 356 mammographic technologists performed 889,347 screen-film mammography (SFM) examinations, 51 performed 113,929 full-field digital mammography (FFDM) examinations, and 38 performed both SFM and FFDM examinations. From the exams, SFM images revealed 4,328 cancers and 564 cancers were reported for FFDM. The researchers found that the technologists had a statistically significant effect on the radiologists' recall rate, sensitivity, specificity, and CDR for both SFM and FFDM. For PPV1, variability by technologist was observed for SFM but not for FFDM.
The researchers concluded that the performance by the technologist who performed the screening mammography had a significant effect on how the radiologists interpreted the images, but further studies are needed in order to identify what the characteristics of the technologist are that have such an effect.
Mammography Study Compares False Positives Between AI and Radiologists in DBT Screening
May 8th 2025For DBT breast cancer screening, 47 percent of radiologist-only flagged false positives involved mass presentations whereas 40 percent of AI-only flagged false positive cases involved benign calcifications, according to research presented at the recent American Roentgen Ray Society (ARRS) conference.