Artifcial intelligence in BreastScreen Norway: a retrospective analysis of a cancer‑enriched sample including 1254 breast cancer cases

Read the full publication here

Purpose

To compare results of selected performance measures in mammographic screening for Transpara versus independent double reading by radiologists.

Materials and Methods

In this retrospective study, we analyzed data from 949 screen-detected breast cancers, 305 interval cancers, and 13,646 negative examinations performed in BreastScreen Norway during the period from 2010 to 2018. Transpara scored the examinations from 1 to 10, based on the risk of malignancy. Results from Transpara were compared to screening results after independent double reading. A Transpara score of 10 was set as the threshold. The results were stratified by mammographic density.

Results

A total of 92.7% of the screen-detected and 40.0% of the interval cancers had a Transpara score of 10. Among women with a negative screening outcome, 9.1% had a Transpara score of 10. For women with the highest breast density, Transpara scored 100% of the screen-detected cancers and 48.6% of the interval cancers with a Transpara score of 10, which resulted in a sensitivity of 80.9% for women with the highest breast density for Transpara, compared to 62.8% for independent double reading. For women with screen-detected cancers who had prior mammograms available, 41.9% had a Transpara score of 10 at the prior screening round.

Conclusion

The high proportion of cancers with a Transpara score of 10 indicates the promising performance of Transpara, particularly for women with dense breasts. Results on prior mammograms with a Transpara score of 10 illustrate the potential for earlier detection of breast cancers by using AI in screen-reading.