Skip to main content

Advertisement

Log in

Prediction of pathological complete response using radiomics on MRI in patients with breast cancer undergoing neoadjuvant pharmacotherapy

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

Neoadjuvant pharmacotherapy is essential for patients with breast cancer who wish to preserve the breast by shrinking the malignant tumor, allowing breast-conserving surgery. It may eliminate cancer cells completely, which is known as pathologic complete response (pCR). Patients with pCR have a lower risk of recurrence. The purpose of this study was to develop a method for predicting patients who achieve pCR by neoadjuvant pharmacotherapy using radiomic features in MR images.

Methods

Fat-suppressed T2-weighted MR images of 64 cases were identified from the ISPY1 dataset. There were 26 cases of pCR and 38 cases of non-pCR. The image slice with the largest tumor diameter was selected from MR images, and the tumor region was manually segmented. A total of 371 radiomic features were calculated from the tumor region. We selected nine radiomic features using Lasso in this study. A support vector machine (SVM) with nine radiomic features was used for predicting patients with pCR.

Results

The result of the ROC analysis showed that the area under the curve of SVM was 0.92 for distinguishing between pCR and non-pCR. Although the input data contain data that were misclassified by SVM, the survival curve classified into the pCR group was at a higher position than the non-pCR group. However, the log-rank test was \(p=0.2\).

Conclusions

We developed a method to predict patients with pCR by neoadjuvant pharmacotherapy using noninvasive MR images. The survival curve of patients classified as having pCR by the proposed method was higher than those classified as non-pCR. Since the proposed method predicts patients who achieve pCR by neoadjuvant pharmacotherapy, it enhances the value of preoperative image information.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Doi K (2007) Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput Med Imaging Graph 31:198–211

    Article  PubMed  PubMed Central  Google Scholar 

  2. Giger ML (2004) Computerized analysis of images in the detection and diagnosis of breast cancer. Semin Ultrasound CT MR 25:411–418

    Article  PubMed  Google Scholar 

  3. Li Q, Nishikawa RM (2015) Computer-aided detection and diagnosis in medical imaging. CRC Press, Florida

    Book  Google Scholar 

  4. Ma W, Zhao Y, Ji Y, Guo X, Jian X, Liu P, Wu S (2019) Breast cancer molecular subtype prediction by mammographic radiomic features. Acad Radiol 26(2):196–201

    Article  PubMed  Google Scholar 

  5. Li H, Zhu Y, Burnside ES, Huang E, Drukker K, Hoadley KA, Fan C, Conzen SD, Zuley M, Net JM, Sutton E, Whitman GJ, Morris E, Perou CM, Ji Y, Giger ML (2016) Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set. NPJ Breast Cancer 2:16012

    Article  PubMed  PubMed Central  Google Scholar 

  6. Wang J, Kato F, Oyama-Manabe N, Li R, Cui Y, Tha KK, Yamashita H, Kudo K, Shirato H (2015) Identifying triple-negative breast cancer using background parenchymal enhancement heterogeneity on dynamic contrast-enhanced MRI: a pilot radiomics study. PLoS ONE 10(11):e0143308

    Article  PubMed  PubMed Central  Google Scholar 

  7. Cao K, Zhao B, Li XT, Li YL, Sun YS (2019) Texture analysis of dynamic contrast-enhanced MRI in evaluating pathologic complete response (pCR) of mass-like breast cancer after neoadjuvant therapy. J Oncol 4731532

  8. Cain EH, Saha A, Harowicz MR, Marks JR, Marcom PK, Mazurowski MA (2019) Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set. Breast Cancer Res Treat 173:455–463

    Article  CAS  PubMed  Google Scholar 

  9. Heacock L, Lewin A, Ayoola A, Moccaldi M, Babb JS, Kim SG, Moy L (2020) Dynamic contrast-enhanced MRI evaluation of pathologic complete response in human epidermal growth factor receptor 2 (HER2)-positive breast cancer after HER2-targeted therapy. Acad Radiol 27:e87–e93

    Article  PubMed  Google Scholar 

  10. Drukker K, Edwards A, Doyle C, Papaioannou J, Kulkarni K, Giger ML (2019) Breast MRI radiomics for the pretreatment prediction of response to neoadjuvant chemotherapy in node-positive breast cancer patients. J Med Imaging 6:034502

    Article  Google Scholar 

  11. Fusco R, Granata V, Maio F, Sansone M, Petrillo A (2020) Textural radiomic features and time-intensity curve data analysis by dynamic contrast-enhanced MRI for early prediction of breast cancer therapy response: preliminary data. Eur Radiol Exp 4(1):8

    Article  PubMed  PubMed Central  Google Scholar 

  12. Braman NM, Etesami M, Prasanna P, Dubchuk C, Gilmore H, Tiwari P, Plecha D, Madabhushi A (2017) Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI. Breast Cancer Res 19(1):57

    Article  PubMed  PubMed Central  Google Scholar 

  13. Braman N, Prasanna P, Whitney J, Singh S, Beig N, Etesami M, Bates DDB, Gallagher K, Bloch BN, Vulchi M, Turk P, Bera KM, Abraham J, Sikov WM, Somlo G, Harris LN, Gilmore H, Plecha D, Varadan V, Madabhushi A (2019) Association of peritumoral radiomics with tumor biology and pathologic response to preoperative targeted therapy for HER2(ERBB2)-positive breast cancer. JAMA Netw Open 2(4):e192561

    Article  PubMed  PubMed Central  Google Scholar 

  14. Santamaría G, Bargalló X, Fernández PL, Farrus B, Caparros X, Velasco M (2017) Neoadjuvant systemic therapy in breast cancer: association of contrast-enhanced MR imaging findings, diffusion-weighted imaging findings, and tumor subtype with tumor response. Radiology 283(3):663–672

    Article  PubMed  Google Scholar 

  15. Chen X, Chen X, Yang J, Li Y, Fan W, Yang Z (2020) Combining dynamic contrast-enhanced magnetic resonance imaging and apparent diffusion coefficient maps for a radiomics nomogram to predict pathological complete response to neoadjuvant chemotherapy in breast cancer patients. J Comput Assist Tomogr 44:275–283

    Article  PubMed  Google Scholar 

  16. Liu Z, Li Z, Qu J, Zhang R, Zhou X, Li L, Sun K, Tang Z, Jiang H, Li H, Xiong Q, Ding Y, Zhao X, Wang K, Liu Z, Tian J (2019) Radiomics of multiparametric MRI for pretreatment prediction of pathologic complete response to neoadjuvant chemotherapy in breast cancer: a multicenter study. Clin Cancer Res 25(12):3538–3547

    Article  CAS  PubMed  Google Scholar 

  17. Zhou J, Lu J, Gao C, Zeng J, Zhou C, Lai X, Cai W, Xu M (2020) Predicting the response to neoadjuvant chemotherapy for breast cancer: wavelet transforming radiomics in MRI. BMC Cancer 20(1):100

    Article  PubMed  PubMed Central  Google Scholar 

  18. Li P, Wang X, Xu C, Liu C, Zheng C, Fulham MJ, Geng D, Wang L, Song S, Huang G (2020) 18F-FDG PET/CT radiomic predictors of pathologic complete response (pCR) to neoadjuvant chemotherapy in breast cancer patients. Eur J Nucl Med Mol Imaging 47(5):1116–1126

    Article  CAS  PubMed  Google Scholar 

  19. Antunovic L, De Sanctis R, Cozzi L, Kirienko M, Sagona A, Torrisi R, Tinterri C, Santoro A, Chiti A, Zelic R, Solloni M (2019) PET/CT radiomics in breast cancer: promising tool for prediction of pathological response to neoadjuvant chemotherapy. Eur J Nucl Med Mol Imaging 46(7):1468–1477

    Article  PubMed  Google Scholar 

  20. Ha S, Park S, Bang JI, Kim EK, Lee HY (2017) Metabolic radiomics for pretreatment 18F-FDG PET/CT to characterize locally advanced breast cancer: histopathologic characteristics, response to neoadjuvant chemotherapy, and prognosis. Sci Rep 7(1):1556

    Article  PubMed  PubMed Central  Google Scholar 

  21. Minckwitz GV, Untch M, Blohmer JU, Cosa SD, Eidtmann H, Fasching PA, Gerber B, Eiermann W, Hilfrich J, Huober J, Jackisch C, Kaufmann M, Konecny GE, Denkert C, Nekljudova V, Mehta K, Loibl S (2012) Definition and impact of pathologic complete response on prognosis after neoadjuvant chemotherapy in various intrinsic breast cancer subtypes. J Clin Oncol 30(15):1796–1804

    Article  Google Scholar 

  22. Broglio KR, Quintana M, Foster M, Olinger M, McGlothlin A, Berry SM, Boileau JF, Brezden-Masley C, Chia S, Dent Sm Gelmon K, Paterson A, Rayson D, Berry DA (2016) Association of pathologic complete response to neoadjuvant therapy in HER2-positive breast cancer with long-term outcomes: a meta-analysis. JAMA Oncol 2(6):751–760

    Article  PubMed  Google Scholar 

  23. TCIA. https://wiki.cancerimagingarchive.net/display/Public/ISPY1. Accessed 29 April 2021

  24. Technical University of Lodz. http://eletel.eu/mazda. Accessed 29 April 2021

  25. Szczypiński PM, Strzelecki M, Materka A, Klepaczko A (2009) MaZda–a software package for image texture analysis. Comput Methods Programs Biomed 94(1):66–76

    Article  PubMed  Google Scholar 

  26. Strzelecki M, Szczypinski P, Materka A, Klepaczko A (2013) A software tool for automatic classification and segmentation of 2D/3D medical images. Nucl Instrum Methods Phys Res 702:137–140

    Article  CAS  Google Scholar 

  27. Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning, data mining, inference and prediction, 2nd edn. Springer, New York

    Google Scholar 

  28. Duda RO, Hart PE, Stork DG (2001) Pattern classification. Wiley, New York

    Google Scholar 

  29. Abe S (2005) Support vector machines for pattern classification. Springer, London

    Google Scholar 

  30. Theodoridis S, Koutroumbas K (1999) Pattern recognition. Academic Press, London

    Google Scholar 

  31. Metz CE (1989) Some practical issues of experimental design and data analysis in radiological ROC studies. Investig Radiol 24:234–245

    Article  CAS  Google Scholar 

  32. Collett D (2003) Modelling survival data in medical research, 2nd edn. Chapman & Hall CRC, Boca Raton

    Google Scholar 

  33. Muramatsu C (2018) Overview on subjective similarity of images for content-based medical image retrieval. Radiol Phys Technol 11:109–124

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

A part of this study was supported by a Grant-in-Aided for Scientific Research (C) (No.21K12707) and a grant from Suzuken Memorial Foundation.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Yoshikazu Uchiyama.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kuramoto, Y., Wada, N. & Uchiyama, Y. Prediction of pathological complete response using radiomics on MRI in patients with breast cancer undergoing neoadjuvant pharmacotherapy. Int J CARS 17, 619–625 (2022). https://doi.org/10.1007/s11548-022-02560-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-022-02560-z

Keywords

Navigation