Additional training helps radiologists interpret screening mammograms

Supplemental training can help radiologists improve their performance when interpreting breast cancer screening examinations, according to a new study published by the Journal of the American College of Radiology.

Reading screening mammograms can be a challenging task, the study’s authors observed, and many countries require continuing medical education to “maintain a high performance level.”

“The prevalence of disease is low in breast cancer screening,” wrote Tanya D. Geertse, Dutch Expert Center for Screening in the Netherlands, and colleagues. “Only a small number of cancers can be detected in a large number of images. Reading mammograms in a screening setting therefore requires different skills compared with a clinical setting.”

Geertse et al. identified 18 studies focused on improving radiologist performance when reading screening mammograms. If a study’s population was not specifically radiologists, that particular study was excluded. Overall, 17 of the 18 studies showed improvement in at least one outcome measure for at least one training activity. There were two measurement approaches featured in the 18 studies: one measured a radiologist’s performance on test sets and the other measured performance during actual breast cancer screening.

For the first measurement approach, performance on test sets, sensitivity and specificity were the most commonly reported outcomes. Sensitivity improved in all such studies where it was an outcome. Specificity improved in 75% of studies where it was an outcome.

For the second approach, performance during actual screening, recall rate was the most reported outcome. Recall rate improved in 83% of studies where it was an outcome.

“On the basis of this review, we conclude that supplemental training appears to improve radiologists’ performance,” the authors wrote, noting that the “considerable heterogeneity in interventions used and effect measures reported” made it so that they could not draw accurate conclusions about the best types of supplemental training.

However, the team added, “this review does increase our understanding of the importance of supplemental training to improve the performance of breast screening radiologists and highlights the importance of well-designed studies.”

The authors also explained that more high-quality research in this area is needed. Small sample sizes and the lack of a control group led to many of the studies just being of a “moderate” quality.

“For the future, there is a clear need for well-designed studies that focus on performance in screening practice and look for methods to isolate the effect of training,” Geertse and colleagues wrote. “If test sets are used, information should be obtained on the correlation between test set performance and the performance in screening practice. Future studies should also address the point in time when offering supplemental training activities (eg, in the first year or in the form of continuing education) to breast cancer screening radiologists is most effective.”