Abstract
Objective
This study aimed to establish a MRI-based deep learning radiomics (DLR) signature to predict the human epidermal growth factor receptor 2 (HER2)-low-positive status and further verified the difference in prognosis by the DLR model.
Methods
A total of 481 patients with breast cancer who underwent preoperative MRI were retrospectively recruited from two institutions. Traditional radiomics features and deep semantic segmentation feature-based radiomics (DSFR) features were extracted from segmented tumors to construct models separately. Then, the DLR model was constructed to assess the HER2 status by averaging the output probabilities of the two models. Finally, a Kaplan‒Meier survival analysis was conducted to explore the disease-free survival (DFS) in patients with HER2-low-positive status. The multivariate Cox proportional hazard model was constructed to further determine the factors associated with DFS.
Results
First, the DLR model distinguished between HER2-negative and HER2-overexpressing patients with AUCs of 0.868 and 0.763 in the training and validation cohorts, respectively. Furthermore, the DLR model distinguished between HER2-low-positive and HER2-zero patients with AUCs of 0.855 and 0.750, respectively. Cox regression analysis showed that the prediction score obtained using the DLR model (HR, 0.175; p = 0.024) and lesion size (HR, 1.043; p = 0.009) were significant, independent predictors of DFS.
Conclusions
We successfully constructed a DLR model based on MRI to noninvasively evaluate the HER2 status and further revealed prospects for predicting the DFS of patients with HER2-low-positive status.
Clinical relevance statement
The MRI-based DLR model could noninvasively identify HER2-low-positive status, which is considered a novel prognostic predictor and therapeutic target.
Key Points
• The DLR model effectively distinguished the HER2 status of breast cancer patients, especially the HER2-low-positive status.
• The DLR model was better than the traditional radiomics model or DSFR model in distinguishing HER2 expression.
• The prediction score obtained using the model and lesion size were significant independent predictors of DFS.
Similar content being viewed by others
Abbreviations
- ACC:
-
Accuracy
- ADCs:
-
Antibody–drug conjugates
- AIC:
-
Akaike information criterion
- ASCO:
-
American Society of Clinical Oncology
- CAP:
-
College of American Pathologists
- CE-MRI:
-
Contrast-enhanced MRI
- DFS:
-
Disease-free survival
- DLR:
-
Deep learning radiomics
- DSFR:
-
Deep semantic segmentation feature-based radiomics
- FISH:
-
Fluorescent in situ hybridization
- HER2:
-
Human epidermal growth factor receptor 2
- HR:
-
Hazard ratio
- ICC:
-
Intraclass correlation coefficients
- IHC:
-
Immunohistochemistry
- ISH:
-
In situ hybridization
- LASSO:
-
Least absolute shrinkage and selection operator
- LR:
-
Logistic regression
- ROC:
-
Receiver operating characteristic
- ROI:
-
Region of interest
- SEN:
-
Sensitivity
- SPE:
-
Specificity
- TE/TR:
-
Echo time / repetition time
References
Montemurro F, Delaloge S, Barrios C et al (2020) Trastuzumab emtansine (T-DM1) in patients with HER2-positive metastatic breast cancer and brain metastases: exploratory final analysis of cohort 1 from KAMILLA, a single-arm phase IIIb clinical trial. Ann Oncol 31:1350–1358
Hurvitz S, Caswell-Jin J, McNamara K et al (2020) Pathologic and molecular responses to neoadjuvant trastuzumab and/or lapatinib from a phase II randomized trial in HER2-positive breast cancer (TRIO-US B07). Nat Commun 11:5824
Mamounas E, Untch M, Mano M et al (2021) Adjuvant T-DM1 versus trastuzumab in patients with residual invasive disease after neoadjuvant therapy for HER2-positive breast cancer: subgroup analyses from KATHERINE. Ann Oncol 32:1005–1014
Beyer I, Li Z, Persson J et al (2011) Controlled extracellular matrix degradation in breast cancer tumors improves therapy by trastuzumab. Mol Ther 19:479–489
Nakada T, Sugihara K, Jikoh T, Abe Y, Agatsuma T (2019) The latest research and development into the antibody-drug conjugate, [fam-] trastuzumab deruxtecan (DS-8201a), for HER2 cancer therapy. Chem Pharm Bull 67:173–185
Banerji U, van Herpen C, Saura C et al (2019) Trastuzumab duocarmazine in locally advanced and metastatic solid tumours and HER2-expressing breast cancer: a phase 1 dose-escalation and dose-expansion study. Lancet Oncol 20:1124–1135
Modi S, Park H, Murthy R et al (2020) Antitumor Activity and safety of trastuzumab deruxtecan in patients with HER2-low-expressing advanced breast cancer: results from a phase Ib STUDY. J Clin Oncol 38:1887–1896
Denkert C, Seither F, Schneeweiss A et al (2021) Clinical and molecular characteristics of HER2-low-positive breast cancer: pooled analysis of individual patient data from four prospective, neoadjuvant clinical trials. Lancet Oncol. https://doi.org/10.1016/s1470-2045(21)00301-6
Ahn S, Woo J, Lee K, Park S (2020) HER2 status in breast cancer: changes in guidelines and complicating factors for interpretation. J Pathol Transl Med 54:34–44
Lindström LS, Karlsson E, Wilking UM et al (2012) Clinically used breast cancer markers such as estrogen receptor, progesterone receptor, and human epidermal growth factor receptor 2 are unstable throughout tumor progression. J Clin Oncol 30:2601–2608
Zhou J, Tan H, Li W et al (2021) Radiomics signatures based on multiparametric MRI for the preoperative prediction of the HER2 status of patients with breast cancer. Acad Radiol 28:1352–1360
Song L, Li C, Yin J (2021) Texture analysis using semiquantitative kinetic parameter maps from DCE-MRI: preoperative prediction of HER2 status in breast cancer. Front Oncol 11:675160
Wang K, Lu X, Zhou H et al (2019) Deep learning Radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: a prospective multicentre study. Gut 68:729–741
Gillies R, Kinahan P, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577
Tian Y, Komolafe T, Zheng J et al (2021) Assessing PD-L1 expression level via preoperative MRI in HCC based on integrating deep learning and radiomics features. Diagnostics (Basel, Switzerland). https://doi.org/10.3390/diagnostics11101875
Yang L, Xu P, Zhang Y et al (2022) A deep learning radiomics model may help to improve the prediction performance of preoperative grading in meningioma. Neuroradiology. https://doi.org/10.1007/s00234-022-02894-0
Wolff A, Hammond M, Allison K 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
Koh J, Park A, Ko K, Jung H (2019) Can enhancement types on preoperative MRI reflect prognostic factors and surgical outcomes in invasive breast cancer? Eur Radiol 29:7000–7008
Negrão E, Souza J, Marques E, Bitencourt A (2019) Breast cancer phenotype influences MRI response evaluation after neoadjuvant chemotherapy. Eur J Radiol 120:108701
Gradishar W, Anderson B, Abraham J et al (2020) Breast cancer, version 3.2020, NCCN clinical practice guidelines in oncology. J Natl Compr Cancer Netw 18:452–478
Li X, Yang L, Jiao X (2022) Comparison of traditional radiomics, deep learning radiomics and fusion methods for axillary lymph node metastasis prediction in breast cancer. Acad Radiol. https://doi.org/10.1016/j.acra.2022.10.015
Koo T, Li M (2016) A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J Chiropr Med 15:155–163
Zhou J, Tan H, Li W et al (2020) Radiomics signatures based on multiparametric MRI for the preoperative prediction of the HER2 status of patients with breast cancer. Acad Radiol. https://doi.org/10.1016/j.acra.2020.05.040
Huang B, Tian J, Zhang H et al (2021) Deep semantic segmentation feature-based radiomics for the classification tasks in medical image analysis. IEEE J Biomed Health Inform 25:2655–2664
Li H, Zhu Y, Burnside E et al (2016) Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set. NPJ Breast Cancer. https://doi.org/10.1038/npjbcancer.2016.12
Song S, Bae M, Chang J, Cho N, Ryu H, Moon W (2017) MR and mammographic imaging features of HER2-positive breast cancers according to hormone receptor status: a retrospective comparative study. Acta Radiol 58:792–799
Bitencourt A, Gibbs P, Rossi Saccarelli C et al (2020) MRI-based machine learning radiomics can predict HER2 expression level and pathologic response after neoadjuvant therapy in HER2 overexpressing breast cancer. EBioMedicine 61:103042
Yang X, Wu L, Zhao K et al (2020) Evaluation of human epidermal growth factor receptor 2 status of breast cancer using preoperative multidetector computed tomography with deep learning and handcrafted radiomics features. Chin J Cancer Res 32:175–185
Hosny A, Parmar C, Quackenbush J, Schwartz L, Aerts H (2018) Artificial intelligence in radiology. Nat Rev Cancer 18:500–510
Li Z, Wang Y, Yu J, Guo Y, Cao W (2017) Deep learning based radiomics (DLR) and its usage in noninvasive IDH1 prediction for low grade glioma. Sci Rep 7:5467
Choi Y, Bae S, Chang J et al (2021) Fully automated hybrid approach to predict the IDH mutation status of gliomas via deep learning and radiomics. Neuro Oncol 23:304–313
Schettini F, Chic N, Brasó-Maristany F et al (2021) Clinical, pathological, and PAM50 gene expression features of HER2-low breast cancer. NPJ Breast Cancer 7:1
Gubern-Mérida A, Martí R, Melendez J et al (2015) Automated localization of breast cancer in DCE-MRI. Med Image Anal 20:265–274
Zheng X, Yao Z, Huang Y et al (2020) Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer. Nat Commun 11:1236
Chao H, Shan H, Homayounieh F et al (2021) Deep learning predicts cardiovascular disease risks from lung cancer screening low dose computed tomography. Nat Commun 12:2963
Buolamwini J, Gebru T (2018) Gender shades: intersectional accuracy disparities in commercial gender classification. Proc Mach Learn Res 81:1–15
Tang Y, Tang Y, Peng Y et al (2020) Automated abnormality classification of chest radiographs using deep convolutional neural networks. NPJ Digital Med 3:70
Funding
This study was supported by (1) the National Natural Science Foundation of China, No. 81901711, 82171920, 62271448; (2) the Special Fund for the Construction of High-level Key Clinical Specialty (Medical Imaging) in Guangzhou, Guangzhou Key Laboratory of Molecular Imaging and Clinical Translational Medicine; (3) Guangdong Basic and Applied Basic Research Foundation, No. 2022A1515110792; (4) Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, No. 2023SHIBS0003; (5) Guangzhou First People's Hospital Frontier Medical Technology Project (QY-C04). (6) Science and Technology Projects in Guangzhou, No. SL2022A04J00652, 202201020001, 202201010513.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Guarantor
The scientific guarantor of this publication is Xin-qing Jiang.
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
Xiaotong Xie, Mingyu Wang, and Bingsheng Huang kindly provided statistical advice for this manuscript.
Informed consent
Written informed consent was waived by the Institutional Review Board.
Ethical approval
Institutional Review Board approval was obtained.
Methodology
• retrospective
• diagnostic or prognostic study
• multicenter study
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
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
Guo, Y., Xie, X., Tang, W. et al. Noninvasive identification of HER2-low-positive status by MRI-based deep learning radiomics predicts the disease-free survival of patients with breast cancer. Eur Radiol 34, 899–913 (2024). https://doi.org/10.1007/s00330-023-09990-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-023-09990-6