Can artificial intelligence reduce the interval cancer rate in mammography screening?

Kristina Lång, Solveig Hofvind, Alejandro Rodríguez-Ruiz, Ingvar Andersson, Kristina Lång, Solveig Hofvind, Alejandro Rodríguez-Ruiz, Ingvar Andersson

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: Artificial intelligence; Breast cancer; Mammography; Mass screening.

Conflict of interest statement

The author (A.R.R.) of this manuscript declares relationship with the following company: employee at ScreenPoint Medical. The other authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

© 2021. The Author(s).

Figures

Fig. 1
Fig. 1
Distribution of interval cancer and classification groups of interval cancer by AI risk score
Fig. 2
Fig. 2
True negative interval cancer. A 56-year-old woman with a negative screen exam. AI assigned a continuous risk score of 8.5 corresponding to exam score 9. The area of the cancer was not CAD-marked (a). Sixteen months later, she was diagnosed with a 27-mm-large triple negative breast cancer with histologic grade 3 and Ki67 72% (b, blue frame)
Fig. 3
Fig. 3
False negative interval cancer. A 57-year-old woman with prior breast reduction surgery undergoing screening classified as negative by double reading at two screening rounds (a and b). An indistinctly marginated mass, enlarging since the prior screen exam, was correctly identified as high risk by the AI system (exam risk score 10, regional score 81) (b, blue frame). Fourteen months later, she was diagnosed with a 12-cm-large metastasised triple negative breast cancer with histologic grade 3 and Ki67 95% (c)
Fig. 4
Fig. 4
The potential reduction (grey) of interval cancers in screening using AI for all interval cancers (a) and for interval cancers with grave outcome (b). Note the different scales on the y-axis

References

    1. Ferlay J, Colombet M, Soerjomataram I, et al. Cancer incidence and mortality patterns in Europe: estimates for 40 countries and 25 major cancers in 2018. Eur J Cancer. 2018;103:356–387. doi: 10.1016/j.ejca.2018.07.005.
    1. Houssami N, Hunter K. The epidemiology, radiology and biological characteristics of interval breast cancers in population mammography screening. NPJ Breast Cancer. 2017;3:12. doi: 10.1038/s41523-017-0014-x.
    1. Evans KK, Birdwell RL, Wolfe JM. If you don’t find it often, you often don’t find it: why some cancers are missed in breast cancer screening. PLoS One. 2013;8:e64366. doi: 10.1371/journal.pone.0064366.
    1. Meshkat B, Prichard RS, Al-Hilli Z, et al. A comparison of clinical-pathological characteristics between symptomatic and interval breast cancer. Breast. 2015;24:278–282. doi: 10.1016/j.breast.2015.02.032.
    1. Perry N, Broeders M, de Wolf C, Tornberg S, Holland R, von Karsa L. European guidelines for quality assurance in breast cancer screening and diagnosis. Fourth edition--summary document. Ann Oncol. 2008;19:614–622. doi: 10.1093/annonc/mdm481.
    1. Euler-Chelpin MV, Lillholm M, Napolitano G, Vejborg I, Nielsen M, Lynge E. Screening mammography: benefit of double reading by breast density. Breast Cancer Res Treat. 2018;171:767–776. doi: 10.1007/s10549-018-4864-1.
    1. Sankatsing VDV, Fracheboud J, de Munck L, et al. Detection and interval cancer rates during the transition from screen-film to digital mammography in population-based screening. BMC Cancer. 2018;18:256–256. doi: 10.1186/s12885-018-4122-2.
    1. Hofvind S, Skaane P, Vitak B, et al. Influence of review design on percentages of missed interval breast cancers: retrospective study of interval cancers in a population-based screening program. Radiology. 2005;237:437–443. doi: 10.1148/radiol.2372041174.
    1. Houssami N, Irwig L, Ciatto S. Radiological surveillance of interval breast cancers in screening programmes. Lancet Oncol. 2006;7:259–265. doi: 10.1016/s1470-2045(06)70617-9.
    1. McKinney SM, Sieniek M, Godbole V, et al. International evaluation of an AI system for breast cancer screening. Nature. 2020;577:89–94. doi: 10.1038/s41586-019-1799-6.
    1. Rodriguez-Ruiz A, Lång K, Gubern-Merida A et al (2019) Stand-alone artificial intelligence for breast cancer detection in mammography: comparison with 101 radiologists. J Natl Cancer Inst. 10.1093/jnci/djy222
    1. Schaffter T, Buist DSM, Lee CI, et al. Evaluation of combined artificial intelligence and radiologist assessment to interpret screening mammograms. JAMA Netw Open. 2020;3:e200265. doi: 10.1001/jamanetworkopen.2020.0265.
    1. Wu N, Phang J, Park J, et al. Deep neural networks improve radiologists’ performance in breast cancer screening. IEEE Trans Med Imaging. 2020;39:1184–1194. doi: 10.1109/tmi.2019.2945514.
    1. Kim H-E, Kim HH, Han B-K, et al. Changes in cancer detection and false-positive recall in mammography using artificial intelligence: a retrospective, multireader study. Lancet Digit Health. 2020;2:e138–e148. doi: 10.1016/S2589-7500(20)30003-0.
    1. Wu N, Phang J, Park J et al (2019) Deep neural networks improve radiologists’ performance in breast cancer screening. IEEE Trans Med Imaging. 10.1109/TMI.2019.2945514:1-1
    1. Rodríguez-Ruiz A, Krupinski E, Mordang J-J, et al. Detection of breast cancer with mammography: effect of an artificial intelligence support system. Radiology. 2018;290:305–314. doi: 10.1148/radiol.2018181371.
    1. Rodriguez-Ruiz A, Lång K, Gubern-Merida A et al (2019) Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study. Eur Radiol. 10.1007/s00330-019-06186-9
    1. Yala A, Schuster T, Miles R, Barzilay R, Lehman C. A deep learning model to triage screening mammograms: a simulation study. Radiology. 2019;293:38–46. doi: 10.1148/radiol.2019182908.
    1. Kyono T, Gilbert FJ, van der Schaar M. Improving workflow efficiency for mammography using machine learning. J Am Coll Radiol. 2020;17:56–63. doi: 10.1016/j.jacr.2019.05.012.
    1. Lång K, Dustler M, Dahlblom V, Åkesson A, Andersson I, Zackrisson S (2020) Identifying normal mammograms in a large screening population using artificial intelligence. Eur Radiol. 10.1007/s00330-020-07165-1
    1. Mordang J-J, Janssen T, Bria A, Kooi T, Gubern-Mérida A, Karssemeijer N. Automatic microcalcification detection in multi-vendor mammography using convolutional neural networks. In: Tingberg A, Lång K, Timberg P, editors. Breast imaging. Cham: Springer International Publishing; 2016. pp. 35–42.
    1. Bria A, Karssemeijer N, Tortorella F. Learning from unbalanced data: a cascade-based approach for detecting clustered microcalcifications. Med Image Anal. 2014;18:241–252. doi: 10.1016/j.media.2013.10.014.
    1. Kooi T, Litjens G, van Ginneken B, et al. Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal. 2017;35:303–312. doi: 10.1016/j.media.2016.07.007.
    1. Cornford E, Sharma N. Interval cancers and duty of candour, a UK perspective. Curr Breast Cancer Reports. 2019;11:89–93. doi: 10.1007/s12609-019-0304-4.
    1. Ciatto S, Visioli C, Paci E, Zappa M. Breast density as a determinant of interval cancer at mammographic screening. Br J Cancer. 2004;90:393–396. doi: 10.1038/sj.bjc.6601548.
    1. Hovda T, Holen ÅS, Lång K, et al. Interval and consecutive round breast cancer after digital breast tomosynthesis and synthetic 2D mammography versus standard 2D digital mammography in BreastScreen Norway. Radiology. 2019;294:256–264. doi: 10.1148/radiol.2019191337.
    1. Houssami N, Bernardi D, Caumo F, et al. Interval breast cancers in the ‘screening with tomosynthesis or standard mammography’ (STORM) population-based trial. Breast. 2018;38:150–153. doi: 10.1016/j.breast.2018.01.002.
    1. Bakker MF, de Lange SV, Pijnappel RM, et al. Supplemental MRI screening for women with extremely dense breast tissue. N Engl J Med. 2019;381:2091–2102. doi: 10.1056/NEJMoa1903986.
    1. Ohuchi N, Suzuki A, Sobue T, et al. 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 trial. Lancet. 2016;387:341–348. doi: 10.1016/s0140-6736(15)00774-6.
    1. Christiana B, Alejandro R-R, Christoph M, Nico K, Sylvia HH-K (2020) Going from double to single reading for screening exams labeled as likely normal by AI: what is the impact?, Proc. SPIE 11513, 15th International Workshop on Breast Imaging (IWBI2020) 115130D. 10.1117/12.2564179
    1. Nishikawa RM, Schmidt RA, Linver MN, Edwards AV, Papaioannou J, Stull MA. Clinically missed cancer: how effectively can radiologists use computer-aided detection? AJR Am J Roentgenol. 2012;198:708–716. doi: 10.2214/ajr.11.6423.
    1. Ciatto S, Houssami N, Ambrogetti D, Bonardi R, Collini G, Del Turco MR. Minority report - false negative breast assessment in women recalled for suspicious screening mammography: imaging and pathological features, and associated delay in diagnosis. Breast Cancer Res Treat. 2007;105:37–43. doi: 10.1007/s10549-006-9425-3.
    1. Lameijer JRC, Voogd AC, Pijnappel RM, et al. Delayed breast cancer diagnosis after repeated recall at biennial screening mammography: an observational follow-up study from the Netherlands. Br J Cancer. 2020;123:325–332. doi: 10.1038/s41416-020-0870-2.

Source: PubMed

Sponsors and Collaborators

Medical Conditions

Drug Interventions

3
Subscribe