Skip to main content

Advertisement

SpringerLink
Log in

Machine learning on MRI radiomic features: identification of molecular subtype alteration in breast cancer after neoadjuvant therapy

  • Breast
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

Recent studies have revealed the change of molecular subtypes in breast cancer (BC) after neoadjuvant therapy (NAT). This study aims to construct a non-invasive model for predicting molecular subtype alteration in breast cancer after NAT.

Methods

Eighty-two estrogen receptor (ER)–negative/ human epidermal growth factor receptor 2 (HER2)–negative or ER-low-positive/HER2-negative breast cancer patients who underwent NAT and completed baseline MRI were retrospectively recruited between July 2010 and November 2020. Subtype alteration was observed in 21 cases after NAT. A 2D-DenseUNet machine-learning model was built to perform automatic segmentation of breast cancer. 851 radiomic features were extracted from each MRI sequence (T2-weighted imaging, ADC, DCE, and contrast-enhanced T1-weighted imaging), both in the manual and auto-segmentation masks. All samples were divided into a training set (n = 66) and a test set (n = 16). XGBoost model with 5-fold cross-validation was performed to predict molecular subtype alterations in breast cancer patients after NAT. The predictive ability of these models was subsequently evaluated by the AUC of the ROC curve, sensitivity, and specificity.

Results

A model consisting of three radiomics features from the manual segmentation of multi-sequence MRI achieved favorable predictive efficacy in identifying molecular subtype alteration in BC after NAT (cross-validation set: AUC = 0.908, independent test set: AUC = 0.864); whereas an automatic segmentation approach of BC lesions on the DCE sequence produced good segmentation results (Dice similarity coefficient = 0.720).

Conclusions

A machine learning model based on baseline MRI is proven useful for predicting molecular subtype alterations in breast cancer after NAT.

Key Points

• Machine learning models using MRI-based radiomics signature have the ability to predict molecular subtype alterations in breast cancer after neoadjuvant therapy, which subsequently affect treatment protocols.

• The application of deep learning in the automatic segmentation of breast cancer lesions from MRI images shows the potential to replace manual segmentation..

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

Access this article

Log in via an institution

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.

Similar content being viewed by others

Abbreviations

CNN:

Convolutional neuron network

DSC:

Dice similarity coefficient

ER:

Estrogen receptor

FISH:

Fluorescence in situ hybridization

HER2:

Human epidermal growth factor receptor 2

ICC:

Intraclass correlation coefficient

IHC:

Immunohistochemical

NAT:

Neoadjuvant therapy

pCR:

Pathological complete response

PR:

Progesterone receptor

TNBC:

Triple-negative breast cancer

References

  1. Ahn S, Kim HJ, Kim M et al (2018) Negative conversion of progesterone receptor status after primary systemic therapy is associated with poor clinical outcome in patients with breast cancer. Cancer Res Treat 50:1418–1432

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. Gahlaut R, Bennett A, Fatayer H et al (2016) Effect of neoadjuvant chemotherapy on breast cancer phenotype, ER/PR and HER2 expression - implications for the practising oncologist. Eur J Cancer 60:40–48

    Article  CAS  PubMed  Google Scholar 

  3. Gradishar WJ, Anderson BO, Abraham J et al (2020) Breast Cancer, Version 3.2020, NCCN Clinical Practice Guidelines in Oncology. J Natl Compr Cancer Netw 18:452–478

    Article  CAS  Google Scholar 

  4. Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts H (2018) Artificial intelligence in radiology. Nat Rev Cancer 18:500–510

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  5. Zhou J, Zhang Y, Chang KT et al (2020) Diagnosis of benign and malignant breast lesions on DCE-MRI by using radiomics and deep learning with consideration of peritumor tissue. J Magn Reson Imaging 51:798–809

    Article  PubMed  Google Scholar 

  6. Arevalo J, Gonzalez FA, Ramos-Pollan R, Oliveira JL, Guevara Lopez MA (2016) Representation learning for mammography mass lesion classification with convolutional neural networks. Comput Methods Prog Biomed 127:248–257

    Article  Google Scholar 

  7. Kooi T, Litjens G, van Ginneken B et al (2017) Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal 35:303–312

    Article  PubMed  Google Scholar 

  8. Becker AS, Marcon M, Ghafoor S, Wurnig MC, Frauenfelder T, Boss A (2017) Deep learning in mammography: diagnostic accuracy of a multipurpose image analysis software in the detection of breast cancer. Invest Radiol 52:434–440

    Article  PubMed  Google Scholar 

  9. Chougrad H, Zouaki H, Alheyane O (2018) Deep convolutional neural networks for breast cancer screening. Comput Methods Prog Biomed 157:19–30

    Article  Google Scholar 

  10. Ye DM, Wang HT, Yu T (2020) The application of radiomics in breast MRI: a review. Technol Cancer Res Treat 19:1533033820916191

    Article  PubMed  PubMed Central  Google Scholar 

  11. Dalmis MU, Litjens G, Holland K et al (2017) Using deep learning to segment breast and fibroglandular tissue in MRI volumes. Med Phys 44:533–546

    Article  CAS  PubMed  Google Scholar 

  12. Fashandi H, Kuling G, Lu Y, Wu H, Martel AL (2019) An investigation of the effect of fat suppression and dimensionality on the accuracy of breast MRI segmentation using U-nets. Med Phys 46:1230–1244

    Article  PubMed  Google Scholar 

  13. Shin HC, Roth HR, Gao M et al (2016) Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 35:1285–1298

    Article  PubMed  Google Scholar 

  14. Moeskops P, Wolterink JM, van der Velden BH et al (2017) Deep learning for multi-task medical image segmentation in multiple modalities. International Conference on Medical Image Computing and Computer-Assisted Intervention 2017: Springer, Cham

  15. Benjelloun M, Adoui ME, Larhmam MA, Mahmoudi SA (n.d.) Automated breast tumor segmentation in DCE-MRI using deep learning. 2018 4th International Conference on Cloud Computing Technologies and Applications (Cloudtech). https://doi.org/10.1109/CloudTech.2018.8713352

  16. Wolff AC, Hammond MEH, Allison KH et al (2018) Human epidermal growth factor receptor 2 testing in breast cancer: American Society of Clinical Oncology/College of American Pathologists Clinical Practice Guideline Focused Update. J Clin Oncol 36:2105–2122

    Article  CAS  PubMed  Google Scholar 

  17. Zopluoglu C (2019) Detecting examinees with item preknowledge in large-scale testing using Extreme Gradient Boosting (XGBoost). Educ Psychol Meas 79:931–961

    Article  PubMed  PubMed Central  Google Scholar 

  18. Yu D, Liu Z, Su C et al (2020) Copy number variation in plasma as a tool for lung cancer prediction using Extreme Gradient Boosting (XGBoost) classifier. Thorac Cancer 11:95–102

    Article  CAS  PubMed  Google Scholar 

  19. Ahmed A, Gibbs P, Pickles M, Turnbull L (2012) Texture analysis in assessment and prediction of chemotherapy response in breast cancer. J Magn Reson Imaging 38:89–101

    Article  PubMed  Google Scholar 

  20. Banerjee I, Malladi S, Lee D et al (2018) Assessing treatment response in triple-negative breast cancer from quantitative image analysis in perfusion magnetic resonance imaging. J Med Imaging (Bellingham) 5:011008

    PubMed  Google Scholar 

  21. Braman NM, Etesami M, Prasanna P et al (2017) Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI. Breast Cancer Res 19:57

    Article  PubMed  PubMed Central  Google Scholar 

  22. 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 

  23. Chamming’s F, Ueno Y, Ferré R et al (2018) Features from computerized texture analysis of breast cancers at pretreatment MR imaging are associated with response to neoadjuvant chemotherapy. Radiology 286:412–420

    Article  PubMed  Google Scholar 

  24. Fan M, Wu G, Cheng H, Zhang J, Shao G, Li L (2017) Radiomic analysis of DCE-MRI for prediction of response to neoadjuvant chemotherapy in breast cancer patients. Eur J Radiol 94:140–147

    Article  CAS  PubMed  Google Scholar 

  25. Henderson S, Purdie C, Michie C et al (2017) Interim heterogeneity changes measured using entropy texture features on T2-weighted MRI at 3.0 T are associated with pathological response to neoadjuvant chemotherapy in primary breast cancer. Eur Radiol 27:4602–4611

    Article  PubMed  PubMed Central  Google Scholar 

  26. Liu Z, Li Z, Qu J et al (2019) Radiomics of multiparametric MRI for pretreatment prediction of pathologic complete response to neoadjuvant chemotherapy in breast cancer: a multicenter study. Clin Cancer Res 25:3538–3547

    Article  CAS  PubMed  Google Scholar 

  27. Michoux N, Van den Broeck S, Lacoste L et al (2015) Texture analysis on MR images helps predicting non-response to NAC in breast cancer. BMC Cancer 15:574

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  28. Panzeri MM, Losio C, Della Corte A et al (2018) Prediction of chemoresistance in women undergoing neo-adjuvant chemotherapy for locally advanced breast cancer: volumetric analysis of first-order textural features extracted from multiparametric MRI. Contrast Media Mol Imaging 2018:8329041

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  29. Teruel JR, Heldahl MG, Goa PE et al (2014) Dynamic contrast-enhanced MRI texture analysis for pretreatment prediction of clinical and pathological response to neoadjuvant chemotherapy in patients with locally advanced breast cancer. NMR Biomed 27:887–896

    Article  PubMed  Google Scholar 

  30. Wu J, Gong G, Cui Y, Li R (2016) Intratumor partitioning and texture analysis of dynamic contrast-enhanced (DCE)-MRI identifies relevant tumor subregions to predict pathological response of breast cancer to neoadjuvant chemotherapy. J Magn Reson Imaging 44:1107–1115

    Article  PubMed  PubMed Central  Google Scholar 

  31. Lu W, Wang Z, Y He et al (2019) Breast cancer detection based on merging four modes MRI using convolutional neural networks. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

  32. Gp A, Ms A, Rf B et al (2020) Multi-planar 3D breast segmentation in MRI via deep convolutional neural networks. Artif Intell Med 103:101781

    Article  Google Scholar 

  33. Piantadosi G, Sansone M, Sansone C (2018) Breast Segmentation in MRI via U-Net Deep Convolutional Neural Networks. 2018 24th International Conference on Pattern Recognition (ICPR)

  34. Piantadosi G, Marrone S, Galli A et al (2019) DCE-MRI breast lesions segmentation with a 3TP U-Net deep convolutional neural network. 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)

  35. Sui D, Huang Z, Song X et al (2021) Breast regions segmentation based on U-net++ from DCE-MRI image sequences. J Phys Conf Ser 1748:042058

  36. Qiao M, Suo S, Cheng F et al (2021) Three-dimensional breast tumor segmentation on DCE-MRI with a multilabel attention-guided joint-phase-learning network. Comput Med Imaging Graph 90:101909

    Article  PubMed  Google Scholar 

  37. Jiao H, Jiang X, Pang Z et al (2020) Deep convolutional neural networks-based automatic breast segmentation and mass detection in DCE-MRI. Comput Math Methods Med 5:2413706

    Google Scholar 

  38. Jun Z, Ashirbani S et al (2018) Hierarchical convolutional neural networks for segmentation of breast tumors in MRI with application to radiogenomics. IEEE Trans Med Imaging 38:435–447

    Google Scholar 

  39. Lei Y, He X, Yao J et al (2021) Breast tumor segmentation in 3D automatic breast ultrasound using mask scoring R-CNN. Med Phys 48:204–21441

    Article  CAS  PubMed  Google Scholar 

  40. Baccouche A, Garcia-Zapirain B, Olea CC et al (2021) Connected-UNets: a deep learning architecture for breast mass segmentation. NPJ Breast Cancer 7:151

    Article  PubMed  PubMed Central  Google Scholar 

  41. Adoui ME, Mahmoudi SA, Larhmam MA et al (2019) MRI breast tumor segmentation using different encoder and decoder CNN architectures. J Comput 8:52

    Google Scholar 

Download references

Acknowledgements

This study was supported by the National Key R&D Program of China under Grant Nos. 2017YFC1309100 and the National Natural Science Foundation of China under Grant Nos. 81671653. This project was supported by the Artificial Intelligence Lab and the Big Data Center of Sun Yat-sen Memorial Hospital, Sun Yat-sen University.

Funding

This study has received funding from the National Key R&D Program of China under Grant Nos. 2017YFC1309100 and the National Natural Science Foundation of China under Grant Nos. 81671653.

Author information

Author notes

  1. Hai-Qing Liu and Si-Ying Lin contributed equally to this work.

    Hui-Ying Zhao and Zhuo Wu contributed equally to this work.

Authors and Affiliations

  1. Department of Radiology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, 510120, China

    Hai-Qing Liu, Si-Yao Mai & Zhuo Wu

  2. Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, 510120, China

    Hai-Qing Liu, Si-Yao Mai, Kai Chen, Zhuo Wu & Hui-Ying Zhao

  3. School of Software Engineering, Sun Yat-sen University, Zhuhai, 519000, China

    Si-Ying Lin & Yue-dong Yang

  4. School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, 510000, China

    Yi-Dong Song

  5. Breast Tumor Cente, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, 510120, China

    Kai Chen

  6. Department of Medical Research Center, Sun Yat-Sen University, Guangzhou, 510120, China

    Hui-Ying Zhao

Authors
  1. Hai-Qing Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Si-Ying Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yi-Dong Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Si-Yao Mai
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yue-dong Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kai Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Zhuo Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Hui-Ying Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Zhuo Wu or Hui-Ying Zhao.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Zhuo Wu and Hui-Ying Zhao.

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent signed by the patient was waived by the Institutional Review Board. anonymization of all DICOM files should be performed by researchers according to IRB requirements, to ensure data security and privacy.

Ethical approval

This study was approved by the ethics committee of the Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China (SYSEC-KY-KS-2021-013).

Methodology

• retrospective

• observational

• performed at one institution

Additional information

Publisher’s note

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

Supplementary information

ESM 1

(DOCX 2047 kb)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, HQ., Lin, SY., Song, YD. et al. Machine learning on MRI radiomic features: identification of molecular subtype alteration in breast cancer after neoadjuvant therapy. Eur Radiol 33, 2965–2974 (2023). https://doi.org/10.1007/s00330-022-09264-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-022-09264-7

Keywords

Search

Navigation