The Potential of AI to Reduce Interval Cancer in a Middle-Income Country Breast Cancer Screening Program

Arıbal M. E., Çelik L., Janssen N.

RSNA, Radiologic Society of North America, Illinois, United States Of America, 28 November - 02 December 2021

  • Publication Type: Conference Paper / Unpublished
  • City: Illinois
  • Country: United States Of America
  • Acibadem Mehmet Ali Aydinlar University Affiliated: No


To evaluate the performance of an artificial intelligence (AI) system for predicting risk of developing interval cancer among women with negative screening exams attending a national screening program of a middle income country. 


This retrospective study was performed with a data cohort between 2016-2019 derived from women between 40-69 who attended the Turkish breast cancer screening program. During this period, the recall rate was on average 5.3%. The negative screening exams of 270 women who developed IC before the next screening round were collected, and 446 women with normal follow-up. The pathological outcome and time-to-diagnosis were retrieved. All mammograms were processed by an AI cancer detection system (Transpara, ScreenPoint Medical), assigning a score between 1-10 to the exam, representing an increasing likelihood of malignancy. The performance of the AI system for detection of IC on negative screening exams was estimated in terms of the area under the receiver operating characteristic curve (AUC), and sensitivity at 90% and 95.0% specificity, with 95% confidence intervals (CI). 


More than half of all IC (53%) were flagged by the highest AI score 10. The AUC of AI to detect signs of IC on negative screening exams was 0.80 (95% CI = 0.77-0.83). The sensitivity was 53.7% and 38.5% at specificity of 90% and 95.0%, respectively. The highest performance of AI was found for cases that were diagnosed within 6 months after screening (AUC: 0.85 (95% CI = 0.78-0.92), compared to cases diagnosed within 24 months after screening (AUC: 0.74 (95% CI = 0.67–0.81). 


AI has the potential to reduce the stable high rate of interval cancer, in case AI is applied as second or third independent reader within a national breast cancer screening program.

Clinical relevance:
Especially in middle income countries, there is a clinical need to reduce the stable high rate of interval cancers. 

Keywords: breast cancer; AI; interval cancer;