Share：
Share this content in WeChat
X
[Chinese] [PDF] 11 1
• Clinical Article •
Non-invasive prediction of HER-2 overexpression and low expression in NME-type breast cancer using multiparametric MRI radiomics combined with MRI features
ZHAO Ying  JIANG Xinyao  ZHAO Nan  XU Yongsheng  LEI Junqiang 

Cite this article as: ZHAO Y, JIANG X Y, ZHAO N, et al. Non-invasive prediction of HER-2 overexpression and low expression in NME-type breast cancer using multiparametric MRI radiomics combined with MRI features[J]. Chin J Magn Reson Imaging, 2025, 16(10): 41-47, 97. DOI:10.12015/issn.1674-8034.2025.10.007.


[Abstract] Objective To explore the value of multiparametric MRI radiomics combined with MRI features in non-invasively predicting human epidermal growth factor receptor 2 (HER-2) overexpression and low expression in non-mass enhancement (NME)-type breast cancer.Materials and Methods A total of 156 breast cancer cases with NME on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and pathologically confirmed were collected from our hospital, and divided into the HER-2 overexpression group (66 cases) and the HER-2 low expression group (90 cases). They were randomly assigned to a training set (124 cases) and a test set (32 cases) at a ratio of 8∶2. Volumes of interest (VOIs) were segmented on the 2nd phase (DCE-2), 8th phase (DCE-8) of DCE-MRI, and diffusion weighted imaging (DWI) sequences, and radiomic features were extracted. The Elastic Net (Enet) algorithm was used to construct models based on DCE-2, DCE-8, DWI, and their combination. Logistic regression analysis was performed to identify independent influencing factors for HER-2 expression. Finally, a fusion model was built by combining the rad-score of the combined model with independent influencing factors.Results The areas under the curve (AUC) of the radiomic models based on DCE-2, DCE-8, DWI, and their combination in the training and test sets were 0.746 and 0.714, 0.768 and 0.714, 0.721 and 0.635, 0.823 and 0.734, respectively. Logistic regression analysis showed that the maximum tumor diameter was an independent factor for distinguishing HER-2 expression (P < 0.05). The fusion model achieved the best predictive performance, with AUCs of 0.844 and 0.808 in the training and test sets, respectively. DeLong's test indicated no significant difference between the combined model and the fusion model (P = 0.316). Analysis of SHAP results showed that rad-score contributed the most to the fusion model.Conclusions Multi-parametric MRI radiomics combined with MRI features can effectively predict HER-2 overexpression and low expression in NME-type breast cancer, and the combination with SHAP algorithm can further improve the interpretability of the model.
[Keywords] non-mass enhancement breast cancer；dynamic contrast-enhanced magnetic resonance imaging；radiomics；magnetic resonance imaging；human epidermal growth factor receptor 2；overexpression and low expression

ZHAO Ying1   JIANG Xinyao1   ZHAO Nan1   XU Yongsheng1, 2, 3   LEI Junqiang1, 2, 3*  

1 The First Clinical Medical College of Lanzhou University, Lanzhou 730000, China

2 Department of Radiology, the First Hospital of Lanzhou University, Lanzhou 730000, China

3 Gansu Provincial Clinical Research Center for Radiological Imaging and Medicine, Lanzhou 730000, China

Corresponding author: LEI J Q, E-mail: leijq2011@126.com

Conflicts of interest   None.

Received  2025-07-31
Accepted  2025-09-28
DOI: 10.12015/issn.1674-8034.2025.10.007
Cite this article as: ZHAO Y, JIANG X Y, ZHAO N, et al. Non-invasive prediction of HER-2 overexpression and low expression in NME-type breast cancer using multiparametric MRI radiomics combined with MRI features[J]. Chin J Magn Reson Imaging, 2025, 16(10): 41-47, 97. DOI:10.12015/issn.1674-8034.2025.10.007.

[1]
BRAY F, LAVERSANNE M, SUNG H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2024, 74(3): 229-263. DOI: 10.3322/caac.21834.
[2]
DENKERT C, SEITHER F, SCHNEEWEISS A, et al. Clinical and molecular characteristics of HER2-low-positive breast cancer: pooled analysis of individual patient data from four prospective, neoadjuvant clinical trials[J]. Lancet Oncol, 2021, 22(8): 1151-1161. DOI: 10.1016/S1470-2045(21)00301-6.
[3]
MODI S N, JACOT W, YAMASHITA T, et al. Trastuzumab deruxtecan in previously treated HER2-low advanced breast cancer[J]. N Engl J Med, 2022, 387(1): 9-20. DOI: 10.1056/NEJMoa2203690.
[4]
FAN P C, XU K. Antibody-drug conjugates in breast cancer: Marching from HER2-overexpression into HER2-low[J/OL]. Biochim Biophys Acta Rev Cancer, 2023, 1878(1): 188849 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/36502928/. DOI: 10.1016/j.bbcan.2022.188849.
[5]
BATISTA M VAZ, PÉREZ-GARCÍA J M, CORTEZ P, et al. Trastuzumab deruxtecan in patients with previously treated HER2-low advanced breast cancer and active brain metastases: the DEBBRAH trial[J/OL]. ESMO Open, 2024, 9(9): 103699 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/39255534/. DOI: 10.1016/j.esmoop.2024.103699.
[6]
BITENCOURT A G V, GIBBS P, ROSSI SACCARELLI C, et al. MRI-based machine learning radiomics can predict HER2 expression level and pathologic response after neoadjuvant therapy in HER2 overexpressing breast cancer[J/OL]. EBioMedicine, 2020, 61: 103042 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/33039708/. DOI: 10.1016/j.ebiom.2020.103042.
[7]
KAZEROUNI A S, HORMUTH D A, DAVIS T, et al. Quantifying tumor heterogeneity via MRI habitats to characterize microenvironmental alterations in HER2+ breast cancer[J/OL]. Cancers (Basel), 2022, 14(7): 1837 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/35406609/. DOI: 10.3390/cancers14071837.
[8]
MIGLIETTA F, GRIGUOLO G, BOTTOSSO M, et al. HER2-low-positive breast cancer: evolution from primary tumor to residual disease after neoadjuvant treatment[J/OL]. NPJ Breast Cancer, 2022, 8(1): 66 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/35595761/. DOI: 10.1038/s41523-022-00434-w.
[9]
XU A, CHU X, ZHANG S, et al. Development and validation of a clinicoradiomic nomogram to assess the HER2 status of patients with invasive ductal carcinoma[J/OL]. BMC Cancer, 2022, 22(1): 872 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/35945526/. DOI: 10.1186/s12885-022-09967-6
[10]
FANG C, ZHANG J, LI J, et al. Clinical-radiomics nomogram for identifying HER2 status in patients with breast cancer: A multicenter study[J/OL]. Front Oncol, 2022, 12: 922185 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/36158700/. DOI: 10.3389/fonc.2022.922185
[11]
LI X, FANG J, WANG F, et al. Prediction of HER2 expression in breast cancer patients based on multi-parametric MRI intratumoral and peritumoral radiomics features combined with clinical and imaging indicators[J/OL]. Front Oncol, 2025, 15: 1531553 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/40552272/. DOI: 10.3389/fonc.2025.1531553
[12]
TARANTINO P, HAMILTON E, TOLANEY S M, et al. HER2-low breast cancer: pathological and clinical landscape[J]. J Clin Oncol, 2020, 38(17): 1951-1962. DOI: 10.1200/JCO.19.02488.
[13]
RAMTOHUL T, DJERROUDI L, LISSAVALID E, et al. Multiparametric MRI and radiomics for the prediction of HER2-zero, -low, and-positive breast cancers[J/OL]. Radiology, 2023, 308(2): e222646 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/37526540/. DOI: 10.1148/radiol.222646.
[14]
ZHENG S Y, YANG Z H, DU G Z, et al. Discrimination between HER2-overexpressing, -low-expressing, and-zero-expressing statuses in breast cancer using multiparametric MRI-based radiomics[J]. Eur Radiol, 2024, 34(9): 6132-6144. DOI: 10.1007/s00330-024-10641-7.
[15]
LIU W M, YANG Y Q, WANG X H, et al. A comprehensive model outperformed the single radiomics model in noninvasively predicting the HER2 status in patients with breast cancer[J]. Acad Radiol, 2025, 32(1): 24-36. DOI: 10.1016/j.acra.2024.07.048.
[16]
BIAN X Q, DU S Y, YUE Z B, et al. Potential antihuman epidermal growth factor receptor 2 target therapy beneficiaries: the role of MRI-based radiomics in distinguishing human epidermal growth factor receptor 2-low status of breast cancer[J]. J Magn Reson Imaging, 2023, 58(5): 1603-1614. DOI: 10.1002/jmri.28628.
[17]
GUO Y, XIE X T, TANG W J, 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[J]. Eur Radiol, 2024, 34(2): 899-913. DOI: 10.1007/s00330-023-09990-6.
[18]
CHEN Y X, CHEN S Y, TANG W J, et al. Multiparametric MRI radiomics with machine learning for differentiating HER2-zero, -low, and-positive breast cancer: model development, testing, and interpretability analysis[J/OL]. AJR Am J Roentgenol, 2025, 224(1): e2431717 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/39413232/. DOI: 10.2214/AJR.24.31717.
[19]
NGUYEN V T, DUONG D H, NGUYEN Q T, et al. The association of magnetic resonance imaging features with five molecular subtypes of breast cancer[J/OL]. Eur J Radiol Open, 2024, 13: 100585 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/39041054/. DOI: 10.1016/j.ejro.2024.100585
[20]
The Society of Breast Cancer China AntiCancer Association; Breast Oncology Group of the Oncology Branch of the Chinese Medical Association, The Society of Breast Cancer China AntiCancer Association; Breast Oncology Group of the Oncology Branch of the Chinese Medical Association. Guidelines for breast cancer diagnosis and treatment by China Anti-cancer Association(2024 edition)[J]. China Oncol, 2023, 33(12): 1092-1187. DOI: 10.19401/j.cnki.1007-3639.2023.12.004.
[21]
WOLFF A C, SOMERFIELD M R, DOWSETT M, et al. Human epidermal growth factor receptor 2 testing in breast cancer: ASCO-college of American pathologists guideline update[J]. J Clin Oncol, 2023, 41(22): 3867-3872. DOI: 10.1200/JCO.22.02864.
[22]
VI C, MANDARANO G, SHIGDAR S. Diagnostics and therapeutics in targeting HER2 breast cancer: a novel approach[J/OL]. Int J Mol Sci, 2021, 22(11): 6163 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/34200484/. DOI: 10.3390/ijms22116163.
[23]
HARBECK N. Neoadjuvant and adjuvant treatment of patients with HER2-positive early breast cancer[J/OL]. Breast, 2022, 62(Suppl 1): S12-S16 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/35148934/. DOI: 10.1016/j.breast.2022.01.006.
[24]
WILDIERS H, TRYFONIDIS K, DAL LAGO L, et al. Pertuzumab and trastuzumab with or without metronomic chemotherapy for older patients with HER2-positive metastatic breast cancer (EORTC 75111-10114): an open-label, randomised, phase 2 trial from the Elderly Task Force/Breast Cancer Group[J]. Lancet Oncol, 2018, 19(3): 323-336. DOI: 10.1016/S1470-2045(18)30083-4.
[25]
CHEN X F, LI R R, LIU X D, et al. To explore the application value of DCE-MR radiomics prediction model in identifying HER2 low expression and HER2 positive breast cancer[J]. Chin J CT MRI, 2023, 21(10): 87-90. DOI: 103969/j.issn.16772-5131.2023.10.027.
[26]
DING M X, CHEN W Y, ZHOU Y, et al. Multi-phase MRI radiomics to predict human epidermal growth factor receptor 2 low expression and over expression status in breast cancer: a multi-center study[J]. J Wenzhou Med Univ, 2024, 54(12): 970-977, 986. DOI: 10.3969/j.issn.2095-9400.2024.12.004.
[27]
WANG H L, SANG L, XU J X, et al. Multiparametric MRI-based radiomic nomogram for predicting HER-2 2+ status of breast cancer[J/OL]. Heliyon, 2024, 10(9): e29875 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/38720718/. DOI: 10.1016/j.heliyon.2024.e29875.
[28]
PENG Y Q, ZHANG X, QIU Y, et al. Development and validation of MRI radiomics models to differentiate HER2-zero, -low, and-positive breast cancer[J/OL]. Am J Roentgenol, 2024, 222(4): e2330603 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/38265001/. DOI: 10.2214/ajr.23.30603.
[29]
SHEN M Y, ZHANG L, ZHANG D Y, et al. Nomogram for predicting HER-2 expression in invasive breast carcinoma of No specific type based on radiomics of DCE-MRI[J]. Chin J Med Imag, 2025, 33(4): 381-389. DOI: 10.3969/j.issn.1005-5185.2025.04.08.
[30]
ZHU X C, XU Y G, ZHENG X X, et al. Synergistic therapeutic effects of pertuzumab and pyrrolitinib in HER-2-positive breast cancer: modulation of the PI3K/AKT pathway[J]. Am J Cancer Res, 2025, 15(1): 141-152. DOI: 10.62347/COSC7070.
[31]
QU M M, FENG W, LIU X R, et al. Research progress of synthetic magnetic resonance imaging quantitative parameters in diagnosis and assessment of breast cancer[J]. Chin J Med Imag, 2025, 33(1): 107-112 DOI: 10.3969/j.issn.1005-5185.2025.01.020.
[32]
CHEN Y H, ZHANG X X, BAO B S, et al. Comparison of clinical and pathological features between non-mass-like and mass-like enhancing breast lesions in patients with invasive breast cancer[J]. J Pract Oncol, 2023, 38(4): 360-365. DOI: 10.13267/j.cnki.syzlzz.2023.057.

PREV Deep neural network MRI radiomics predicts glioblastoma MGMT promoter methylation status
NEXT Feasibility study on the classification of liver multi-parameter MRI sequences based on deep learning
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn