Population-wide evaluation of artificial intelligence and radiologist assessment of screening mammograms
Open Access
- 8 November 2023
- journal article
- research article
- Published by Springer Nature in European Radiology
- Vol. 34 (6) , 3935-3946
Abstract
Objectives: To validate an AI system for standalone breast cancer detection on an entire screening population in comparison to first-reading breast radiologists. Materials and methods: All mammography screenings performed between August 4, 2014, and August 15, 2018, in the Region of Southern Denmark with follow-up within 24 months were eligible. Screenings were assessed as normal or abnormal by breast radiologists through double reading with arbitration. For an AI decision of normal or abnormal, two AI-score cut-off points were applied by matching at mean sensitivity (AIsens) and specificity (AIspec) of first readers. Accuracy measures were sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and recall rate (RR). Results: The sample included 249,402 screenings (149,495 women) and 2033 breast cancers (72.6% screen-detected cancers, 27.4% interval cancers). AIsens had lower specificity (97.5% vs 97.7%; p < 0.0001) and PPV (17.5% vs 18.7%; p = 0.01) and a higher RR (3.0% vs 2.8%; p < 0.0001) than first readers. AIspec was comparable to first readers in terms of all accuracy measures. Both AIsens and AIspec detected significantly fewer screen-detected cancers (1166 (AIsens), 1156 (AIspec) vs 1252; p < 0.0001) but found more interval cancers compared to first readers (126 (AIsens), 117 (AIspec) vs 39; p < 0.0001) with varying types of cancers detected across multiple subgroups. Conclusion: Standalone AI can detect breast cancer at an accuracy level equivalent to the standard of first readers when the AI threshold point was matched at first reader specificity. However, AI and first readers detected a different composition of cancers. Clinical relevance statement: Replacing first readers with AI with an appropriate cut-off score could be feasible. AI-detected cancers not detected by radiologists suggest a potential increase in the number of cancers detected if AI is implemented to support double reading within screening, although the clinicopathological characteristics of detected cancers would not change significantly. Key Points: • Standalone AI cancer detection was compared to first readers in a double-read mammography screening population. • Standalone AI matched at first reader specificity showed no statistically significant difference in overall accuracy but detected different cancers. • With an appropriate threshold, AI-integrated screening can increase the number of detected cancers with similar clinicopathological characteristics.Keywords
Funding Information
- Region Syddanmark (10240300)
- University Library of Southern Denmark
This publication has 43 references indexed in Scilit:
- Radiologist shortage leaves patient care at risk, warns royal collegeBMJ, 2017
- The Burden of Primary Liver Cancer and Underlying Etiologies From 1990 to 2015 at the Global, Regional, and National LevelJAMA Oncology, 2017
- Overdiagnosis in breast cancer screening: The impact of study design and calculationsEuropean Journal of Cancer, 2017
- Danish Breast Cancer Cooperative GroupClinical Epidemiology, 2016
- Danish Quality Database for Mammography ScreeningClinical Epidemiology, 2016
- STARD 2015: An Updated List of Essential Items for Reporting Diagnostic Accuracy StudiesRadiology, 2015
- Markers of Good Performance in Mammography Depend on Number of Annual ReadingsRadiology, 2013
- Childhood cancer mortality in AustraliaCancer Epidemiology, 2012
- The descriptive epidemiology of female breast cancer: An international comparison of screening, incidence, survival and mortalityCancer Epidemiology, 2012
- Workforce Shortages in Breast Imaging: Impact on Mammography UtilizationAmerican Journal of Roentgenology, 2009