The purpose of this study was to evaluate the concurrent use of AI with DBT based on mammographic appearance and histopathology. The results showed larger improvements in sensitivity for calcifications-only lesions and DCIS compared to soft tissue lesions and invasive carcinomas. Specificity improvements were similar for soft tissue lesions and cases without suspicious lesions, with no improvement for calcifications-only lesions.

Of interest were the 55.9% reduction in reading time with all non-cancer cases and even 59.1% with BI-RADS 1 or 2 cases that were not recalled, compared to 41.3% with cancer cases. In a mammographic screening setting with DBT, cancer detection rates are about 6 per 1000 women screened and recall rates are about 7% [1-4]. From our results, we can thus compute a 58.5% weighted reduction in reading time in a screening setting with use of the AI system.

In conclusion, sensitivity and reading time improved for all lesion types and histopathologies when AI was used concurrently with DBT. Specificity improved for mammographic soft tissue cases and cases without any suspicious lesions, but not for calcifications-only cases.