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..
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
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
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
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
Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts H (2018) Artificial intelligence in radiology. Nat Rev Cancer 18:500–510
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
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
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
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
Chougrad H, Zouaki H, Alheyane O (2018) Deep convolutional neural networks for breast cancer screening. Comput Methods Prog Biomed 157:19–30
Ye DM, Wang HT, Yu T (2020) The application of radiomics in breast MRI: a review. Technol Cancer Res Treat 19:1533033820916191
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
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
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
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
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
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
Zopluoglu C (2019) Detecting examinees with item preknowledge in large-scale testing using Extreme Gradient Boosting (XGBoost). Educ Psychol Meas 79:931–961
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
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
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
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
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
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
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
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
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
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
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
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
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
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)
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
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)
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)
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
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
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
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
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
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
Adoui ME, Mahmoudi SA, Larhmam MA et al (2019) MRI breast tumor segmentation using different encoder and decoder CNN architectures. J Comput 8:52
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
Authors and Affiliations
Corresponding authors
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.
About this article
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
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-022-09264-7