A Danish retrospective study compared mammography screening performance before and after AI implementation (Transpara, ScreenPoint Medical) using mammograms of 118,997 Danish women aged 50–69 years. In total, 60,751 women were screened before and 58,246 women after AI system implementation.
he study aimed to address the substantial workload on breast radiologists and improve breast cancer screening performance. The AI tool was used to stratify screenings by probability of breast cancer, with an examination score threshold of 5 (later increased to 7) to classify whether a mammogram should be single-read or double-read with AI-assisted decision support.
Implementation of the AI tool led to a 20.5% decrease in the recall rate (3.09% before AI vs. 2.46% with AI), an increase in the cancer detection rate (0.70% before AI vs. 0.82% with AI), a reduction in the false-positive rate (2.39% before AI vs. 1.63% with AI), and an increase in the positive predictive value (22.6% before AI vs. 33.6% with AI).
Additionally, the rate of small cancers detected increased (36.6% before AI vs. 44.9% with AI). Overall, the reading workload was reduced by 33.5% (38,977 fewer readings) demonstrating that AI assistance can enhance screening efficiency and accuracy.
Read full study
Early Indicators of the Impact of Using AI inMammography Screening for Breast Cancer
Radiology, 2024
Abstract
Background:
Retrospective studies have suggested that using artificial intelligence (AI) may decrease the workload of radiologists while preserving mammography screening performance.
Purpose:
To compare workload and screening performance for two cohorts of women who underwent screening before and after AI system implementation.
Materials and Methods:
This retrospective study included 50–69-year-old women who underwent biennial mammography screening in the Capital Region of Denmark. Before AI system implementation (October 1, 2020, to November 17, 2021), all screenings involved double reading. For screenings conducted after AI system implementation (November 18, 2021, to October 17, 2022), likely normalscreenings (AI examination score ≤5 before May 3, 2022, or ≤7 on or after May 3, 2022) were single read by one of 19 senior full-time breast radiologists. The remaining screenings were read by two radiologists with AI-assisted decision support. Biopsy and surgical outcomes were retrieved between October 1, 2020, and April 15, 2023, ensuring at least 180 days of follow-up. Screening metrics were compared using the χ2 test. Reading workload reduction was measured as saved screening reads.
Results:
In total, 60 751 and 58 246 women were screened before and after AI system implementation, respectively (median age, 58years [IQR, 54–64 years] for both cohorts), with a median screening interval before AI of 845 days (IQR, 820–878 days) and with AI of 993 days (IQR, 968–1013 days; P < .001). After AI system implementation, the recall rate decreased by 20.5% (3.09% before AI[1875 of 60 751] vs 2.46% with AI [1430 of 58 246]; P < .001), the cancer detection rate increased (0.70% [423 of 60 751] vs 0.82%[480 of 58 246]; P = .01), the false-positive rate decreased (2.39% [1452 of 60 751] vs 1.63% [950 of 58 246]; P < .001), the positive predictive value increased (22.6% [423 of 1875] vs 33.6% [480 of 1430]; P < .001), the rate of small cancers (≤1 cm) increased(36.6% [127 of 347] vs 44.9% [164 of 365]; P = .02), the rate of node-negative cancers was unchanged (76.7% [253 of 330] vs 77.8%[273 of 351]; P = .73), and the rate of invasive cancers decreased (84.9% [359 of 423] vs 79.6% [382 of 480]; P = .04). The reading workload was reduced by 33.5% (38 977 of 116 492 reads).
Conclusion:
In a population-based mammography screening program, using AI reduced the overall workload of breast radiologists while improving screening performance.