Prediction of Upstaging in Ductal Carcinoma in Situ Based on Mammographic Radiomic Features

Published Online:Jan 4 2022https://doi.org/10.1148/radiol.210407

Abstract

Mammographic radiomic features may help predict occult invasive disease in core-needle biopsy–proven ductal carcinoma in situ.

Background

Improving diagnosis of ductal carcinoma in situ (DCIS) before surgery is important in choosing optimal patient management strategies. However, patients may harbor occult invasive disease not detected until definitive surgery.

Purpose

To assess the performance and clinical utility of mammographic radiomic features in the prediction of occult invasive cancer among women diagnosed with DCIS on the basis of core biopsy findings.

Materials and Methods

In this Health Insurance Portability and Accountability Act–compliant retrospective study, digital magnification mammographic images were collected from women who underwent breast core-needle biopsy for calcifications that was performed at a single institution between September 2008 and April 2017 and yielded a diagnosis of DCIS. The database query was directed at asymptomatic women with calcifications without a mass, architectural distortion, asymmetric density, or palpable disease. Logistic regression with regularization was used. Differences across training and internal test set by upstaging rate, age, lesion size, and estrogen and progesterone receptor status were assessed by using the Kruskal-Wallis or χ² test.

Results

The study consisted of 700 women with DCIS (age range, 40–89 years; mean age, 59 years ± 10 [standard deviation]), including 114 with lesions (16.3%) upstaged to invasive cancer at subsequent surgery. The sample was split randomly into 400 women for the training set and 300 for the testing set (mean ages: training set, 59 years ± 10; test set, 59 years ± 10; P = .85). A total of 109 radiomic and four clinical features were extracted. The best model on the test set by using all radiomic and clinical features helped predict upstaging with an area under the receiver operating characteristic curve of 0.71 (95% CI: 0.62, 0.79). For a fixed high sensitivity (90%), the model yielded a specificity of 22%, a negative predictive value of 92%, and an odds ratio of 2.4 (95% CI: 1.8, 3.2). High specificity (90%) corresponded to a sensitivity of 37%, positive predictive value of 41%, and odds ratio of 5.0 (95% CI: 2.8, 9.0).

Conclusion

Machine learning models that use radiomic features applied to mammographic calcifications may help predict upstaging of ductal carcinoma in situ, which can refine clinical decision making and treatment planning.

References

1. Siegel RL, Miller KD, Jemal A. Cancer statistics, 2020. CA Cancer J Clin 2020;70(1):7–30. Crossref, Medline, Google Scholar
2. Ryser MD, Weaver DL, Zhao F, et al. Cancer outcomes in DCIS patients without locoregional treatment. J Natl Cancer Inst 2019;111(9):952–960. Crossref, Medline, Google Scholar
3. Sanders ME, Schuyler PA, Dupont WD, Page DL. The natural history of low-grade ductal carcinoma in situ of the breast in women treated by biopsy only revealed over 30 years of long-term follow-up. Cancer 2005;103(12):2481–2484. Crossref, Medline, Google Scholar
4. Hieken TJ, Krishnamurthy V, Farolan M, Velasco JM. Long-term outcome of DCIS patients: p53 as a biomarker of ipsilateral recurrence. J Clin Oncol 2011;29(27_suppl):39. Crossref, Google Scholar
5. Schulz S, Sinn P, Golatta M, et al. Prediction of underestimated invasiveness in patients with ductal carcinoma in situ of the breast on percutaneous biopsy as rationale for recommending concurrent sentinel lymph node biopsy. Breast 2013;22(4):537–542. Crossref, Medline, Google Scholar
6. Sim YT, Litherland J, Lindsay E, et al. Upgrade of ductal carcinoma in situ on core biopsies to invasive disease at final surgery: a retrospective review across the Scottish Breast Screening Programme. Clin Radiol 2015;70(5):502–506. Crossref, Medline, Google Scholar
7. Chan MY, Lim S. Predictors of invasive breast cancer in ductal carcinoma in situ initially diagnosed by core biopsy. Asian J Surg 2010;33(2):76–82. Crossref, Medline, Google Scholar
8. Mannu GS, Wang Z, Broggio J, et al. Invasive breast cancer and breast cancer mortality after ductal carcinoma in situ in women attending for breast screening in England, 1988-2014: population based observational cohort study. BMJ 2020;369m1570. Crossref, Medline, Google Scholar
9. Han JS, Molberg KH, Sarode V. Predictors of invasion and axillary lymph node metastasis in patients with a core biopsy diagnosis of ductal carcinoma in situ: an analysis of 255 cases. Breast J 2011;17(3):223–229. Crossref, Medline, Google Scholar
10. Brennan ME, Turner RM, Ciatto S, et al. Ductal carcinoma in situ at core-needle biopsy: meta-analysis of underestimation and predictors of invasive breast cancer. Radiology 2011;260(1):119–128. Link, Google Scholar
11. Byng D, Retèl VP, Schaapveld M, Wesseling J, van Harten WHGrand Challenge PRECISION consortium. Treating (low-risk) DCIS patients: what can we learn from real-world cancer registry evidence? Breast Cancer Res Treat 2021;187(1):187–196. Crossref, Medline, Google Scholar
12. van Seijen M, Lips EH, Thompson AM, et al. Ductal carcinoma in situ: to treat or not to treat, that is the question. Br J Cancer 2019;121(4):285–292. Crossref, Medline, Google Scholar
13. Grimm LJ, Neely B, Hou R, et al. Mixed-methods study to predict upstaging of DCIS to invasive disease on mammography. AJR Am J Roentgenol 2021;216(4):903–911. Crossref, Medline, Google Scholar
14. Hou R, Mazurowski MA, Grimm LJ, et al. Prediction of upstaged ductal carcinoma in situ using forced labeling and domain adaptation. IEEE Trans Biomed Eng 2020;67(6):1565–1572. Crossref, Medline, Google Scholar
15. Shi B, Grimm LJ, Mazurowski MA, et al. Can occult invasive disease in ductal carcinoma in situ be predicted using computer-extracted mammographic features? Acad Radiol 2017;24(9):1139–1147. Crossref, Medline, Google Scholar
16. Meinshausen N, Bühlmann P. Stability selection. J R Stat Soc Series B Stat Methodol 2010;72(4):417–473. Crossref, Google Scholar
17. Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in Python. J Mach Learn Res 2011;12(85):2825–2830.https://www.jmlr.org/papers/v12/pedregosa11a.html. Google Scholar
18. Blumer A, Ehrenfeucht A, Haussler D, Warmuth MK. Learnability and the Vapnik-Chervonenkis dimension. J ACM 1989;36(4):929–965. Crossref, Google Scholar
19. DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 1988;44(3):837–845. Crossref, Medline, Google Scholar
20. Bria A, Karssemeijer N, Tortorella F. Learning from unbalanced data: a cascade-based approach for detecting clustered microcalcifications. Med Image Anal 2014;18(2):241–252. Crossref, Medline, Google Scholar
21. Everett MG, Borgatti SP. The centrality of groups and classes. J Math Sociol 1999;23(3):181–201. Crossref, Google Scholar
22. Hu MK. Visual pattern recognition by moment invariants. IRE Trans Inf Theory 1962;8(2):179–187. Crossref, Google Scholar
23. Greenwood HI, Wilmes LJ, Kelil T, Joe BN. Role of breast MRI in the evaluation and detection of DCIS: opportunities and challenges. J Magn Reson Imaging 2020;52(3):697–709. Crossref, Medline, Google Scholar
24. Harowicz MR, Saha A, Grimm LJ, et al. Can algorithmically assessed MRI features predict which patients with a preoperative diagnosis of ductal carcinoma in situ are upstaged to invasive breast cancer? J Magn Reson Imaging 2017;46(5):1332–1340. Crossref, Medline, Google Scholar
25. Klimov S, Miligy IM, Gertych A, et al. A whole slide image-based machine learning approach to predict ductal carcinoma in situ (DCIS) recurrence risk. Breast Cancer Res 2019;21(1):83. Crossref, Medline, Google Scholar
26. Kurniawan ED, Rose A, Mou A, et al. Risk factors for invasive breast cancer when core needle biopsy shows ductal carcinoma in situ. Arch Surg 2010;145(11):1098–1104. Crossref, Medline, Google Scholar
27. Park HS, Park S, Cho J, Park JM, Kim SI, Park BW. Risk predictors of underestimation and the need for sentinel node biopsy in patients diagnosed with ductal carcinoma in situ by preoperative needle biopsy. J Surg Oncol 2013;107(4):388–392. Crossref, Medline, Google Scholar
28. Weinmann S, Leo MC, Francisco M, et al. Validation of a ductal carcinoma in situ biomarker profile for risk of recurrence after breast-conserving surgery with and without radiotherapy. Clin Cancer Res 2020;26(15):4054–4063. Crossref, Medline, Google Scholar
29. Rakovitch E, Nofech-Mozes S, Hanna W, et al. Multigene expression assay and benefit of radiotherapy after breast conservation in ductal carcinoma in situ. J Natl Cancer Inst 2017;109(4):djw256. Crossref, Google Scholar
30. Shi B, Grimm LJ, Mazurowski MA, et al. Prediction of occult invasive disease in ductal carcinoma in situ using deep learning features. J Am Coll Radiol 2018;15(3 Pt B):527–534. Crossref, Medline, Google Scholar

Article History

Received: Mar 1 2021
Revision requested: Apr 23 2021
Revision received: Sept 24 2021
Accepted: Oct 19 2021
Published online: Jan 04 2022
Published in print: Apr 2022

Vol. 303, No. 1

Abbreviations

Abbreviations:
AUC	area under receiver operating characteristic curve
DCIS	ductal carcinoma in situ

Metrics

Altmetric Score

PDF download