Can artificial intelligence reduce the interval cancer rate in mammography screening?
Open Access
- 23 January 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in European Radiology
- Vol. 31 (8), 5940-5947
- https://doi.org/10.1007/s00330-021-07686-3
Abstract
Objectives: To investigate whether artificial intelligence (AI) can reduce interval cancer in mammography screening. Materials and methods: Preceding screening mammograms of 429 consecutive women diagnosed with interval cancer in Southern Sweden between 2013 and 2017 were analysed with a deep learning–based AI system. The system assigns a risk score from 1 to 10. Two experienced breast radiologists reviewed and classified the cases in consensus as true negative, minimal signs or false negative and assessed whether the AI system correctly localised the cancer. The potential reduction of interval cancer was calculated at different risk score thresholds corresponding to approximately 10%, 4% and 1% recall rates. Results: A statistically significant correlation between interval cancer classification groups and AI risk score was observed (p < .0001). AI scored one in three (143/429) interval cancer with risk score 10, of which 67% (96/143) were either classified as minimal signs or false negative. Of these, 58% (83/143) were correctly located by AI, and could therefore potentially be detected at screening with the aid of AI, resulting in a 19.3% (95% CI 15.9–23.4) reduction of interval cancer. At 4% and 1% recall thresholds, the reduction of interval cancer was 11.2% (95% CI 8.5–14.5) and 4.7% (95% CI 3.0–7.1). The corresponding reduction of interval cancer with grave outcome (women who died or with stage IV disease) at risk score 10 was 23% (8/35; 95% CI 12–39). Conclusion: The use of AI in screen reading has the potential to reduce the rate of interval cancer without supplementary screening modalities. Key Points: • Retrospective study showed that AI detected 19% of interval cancer at the preceding screening exam that in addition showed at least minimal signs of malignancy. Importantly, these were correctly localised by AI, thus obviating supplementary screening modalities. • AI could potentially reduce a proportion of particularly aggressive interval cancers. • There was a correlation between AI risk score and interval cancer classified as true negative, minimal signs or false negative.Keywords
Funding Information
- Swedish Governmental Funding of Clinical Research
This publication has 32 references indexed in Scilit:
- Automatic Microcalcification Detection in Multi-vendor Mammography Using Convolutional Neural NetworksPublished by Springer Science and Business Media LLC ,2016
- Sensitivity and specificity of mammography and adjunctive ultrasonography to screen for breast cancer in the Japan Strategic Anti-cancer Randomized Trial (J-START): a randomised controlled trialThe Lancet, 2016
- A comparison of clinical–pathological characteristics between symptomatic and interval breast cancerThe Breast, 2015
- Learning from unbalanced data: A cascade-based approach for detecting clustered microcalcificationsMedical Image Analysis, 2014
- If You Don’t Find It Often, You Often Don’t Find It: Why Some Cancers Are Missed in Breast Cancer ScreeningPLOS ONE, 2013
- Clinically Missed Cancer: How Effectively Can Radiologists Use Computer-Aided Detection?American Journal of Roentgenology, 2012
- European guidelines for quality assurance in breast cancer screening and diagnosis. Fourth edition—summary documentAnnals of Oncology, 2008
- Minority report – false negative breast assessment in women recalled for suspicious screening mammography: imaging and pathological features, and associated delay in diagnosisBreast Cancer Research and Treatment, 2006
- Radiological surveillance of interval breast cancers in screening programmesThe Lancet Oncology, 2006
- Influence of Review Design on Percentages of Missed Interval Breast Cancers: Retrospective Study of Interval Cancers in a Population-based Screening ProgramRadiology, 2005