基于MRI的乳腺癌HER2状态预测：传统影像特征、影像组学与深度学习方法的系统综述
MRI-Based Prediction of HER2 Status in Breast Cancer: A Systematic Review of Conventional Imaging Features, Radiomics and Deep Learning Methods
DOI: 10.12677/acm.2026.161195, PDF,   
作者: 丁敏溪：绍兴文理学院医学院，浙江 绍兴；徐 民*：温州医科大学附属第五医院(丽水市中心医院)放射科，浙江 丽水
关键词: 乳腺癌；人表皮生长因子受体2；核磁共振成像；影像组学；深度学习；Breast Cancer； Human Epidermal Growth Factor Receptor 2； Magnetic Resonance Imaging； Radiomics； Deep Learning
摘要: 精准判定乳腺癌人表皮生长因子受体2 (HER2)表达状态，对于实现患者个体化治疗、提升疗效及改善预后具有重要意义。传统病理检测存在取样偏倚和侵入性等局限，需要新的方法无创、可重复的检测技术预测HER2状态。近年来，基于磁共振成像的影像组学和深度学习方法能够自动提取高维影像特征，为无创评估HER2状态提供新的途径。本文就基于MRI的乳腺癌HER2状态预测相关文献进行系统综述，从传统影像特征、影像组学到深度学习方法三个层面进行分析，以期为该领域的研究现状评估与未来发展提供参考。
Abstract: Accurate determination of human epidermal growth factor receptor 2 (HER2) expression in breast cancer is essential for individualized treatment, enhanced therapeutic efficacy, and improved patient outcomes. However, conventional pathological assessment is constrained by sampling bias and its invasive nature, highlighting the need for novel noninvasive and reproducible techniques for predicting HER2 status. In recent years, radiomics and MRI-based deep learning approaches have enabled automated extraction of high-dimensional imaging features, offering new avenues for noninvasive HER2 evaluation. This review provides a systematic overview of MRI-based methods for predicting HER2 status in breast cancer, tracing the methodological evolution from conventional imaging features to radiomics and deep learning approaches, and summarizing current research advances to guide future developments in this field.
文章引用：丁敏溪, 徐民. 基于MRI的乳腺癌HER2状态预测：传统影像特征、影像组学与深度学习方法的系统综述[J]. 临床医学进展, 2026, 16(1): 1525-1532. https://doi.org/10.12677/acm.2026.161195

参考文献

[1] Sung, H., Ferlay, J., Siegel, R.L., Laversanne, M., Soerjomataram, I., Jemal, A., et al. (2021) Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA: A Cancer Journal for Clinicians, 71, 209-249. [Google Scholar] [CrossRef] [PubMed]
[2] Cheng, X. (2024) A Comprehensive Review of HER2 in Cancer Biology and Therapeutics. Genes, 15, Article 903. [Google Scholar] [CrossRef] [PubMed]
[3] Wang, B., Ding, W., Sun, K., Wang, X., Xu, L. and Teng, X. (2019) Impact of the 2018 ASCO/CAP Guidelines on HER2 Fluorescence in Situ Hybridization Interpretation in Invasive Breast Cancers with Immunohistochemically Equivocal Results. Scientific Reports, 9, Article No. 16726. [Google Scholar] [CrossRef] [PubMed]
[4] Fenix-Caballero, S., Caleffa-Menendez, P., Dominguez-Santana, C.M., Alegre-Del-Rey, E.J. and Olry de Labry Lima, A. (2025) Economic Evaluation of Treatment with Trastuzumab Deruxtecan for HER2-Low Advanced or Metastatic Breast Cancer in Previously Treated Patients. PharmacoEconomics Open, 9, 827-836. [Google Scholar] [CrossRef] [PubMed]
[5] Saatci, O., Huynh-Dam, K. and Sahin, O. (2021) Endocrine Resistance in Breast Cancer: From Molecular Mechanisms to Therapeutic Strategies. Journal of Molecular Medicine, 99, 1691-1710. [Google Scholar] [CrossRef] [PubMed]
[6] Zagami, P. and Carey, L.A. (2022) Triple Negative Breast Cancer: Pitfalls and Progress. npj Breast Cancer, 8, Article No. 95. [Google Scholar] [CrossRef] [PubMed]
[7] 中国抗癌协会乳腺癌专业委员会, 中华医学会肿瘤学分会乳腺肿瘤学组. 中国抗癌协会乳腺癌诊治指南与规范(2024年版) [J]. 中国癌症杂志, 2023, 33(12) :1092-1187.
[8] Zhong, J., Gao, B., Wang, Q., He, J., Luo, D., Zhang, C., et al. (2025) Exploring the Heterogeneity of HER2 Gene Status and Expression in Non-Positive Breast Cancer Patients: Insights from Immunohistochemistry and Fluorescence in Situ Hybridization. Diagnostic Pathology, 20, Article No. 4. [Google Scholar] [CrossRef] [PubMed]
[9] Lv, T., Wu, Y., Wang, Y., Liu, Y., Li, L., Deng, C., et al. (2022) A Hybrid Hemodynamic Knowledge-Powered and Feature Reconstruction-Guided Scheme for Breast Cancer Segmentation Based on DCE-MRI. Medical Image Analysis, 82, Article 102572. [Google Scholar] [CrossRef] [PubMed]
[10] Adam, R., Dell’Aquila, K., Hodges, L., Maldjian, T. and Duong, T.Q. (2023) Deep Learning Applications to Breast Cancer Detection by Magnetic Resonance Imaging: A Literature Review. Breast Cancer Research, 25, Article No. 87. [Google Scholar] [CrossRef] [PubMed]
[11] Ali, A., Alghamdi, M., Marzuki, S., Tengku Din, T.A., Yamin, M.S., Alrashidi, M., et al. (2025) Exploring AI Approaches for Breast Cancer Detection and Diagnosis: A Review Article. Breast Cancer, 17, 927-947. [Google Scholar] [CrossRef] 
[12] Park, G.E., Mun, H.S., Kim, S.H. and Kang, B.J. (2025) HER2 (2+)/SISH-Positive Vs. HER2 (3+) Breast Cancer: Pre-Treatment MRI Differences and Accuracy of PCR Prediction on Post-Treatment MRI. Academic Radiology, 32, 4395-4407. [Google Scholar] [CrossRef] [PubMed]
[13] Wang, C., Wei, W., Santiago, L., Whitman, G. and Dogan, B. (2018) Can Imaging Kinetic Parameters of Dynamic Contrast-Enhanced Magnetic Resonance Imaging Be Valuable in Predicting Clinicopathological Prognostic Factors of Invasive Breast Cancer? Acta Radiologica, 59, 813-821. [Google Scholar] [CrossRef] [PubMed]
[14] Moradi, B., Gity, M., Etesam, F., Borhani, A., Ahmadinejad, N. and Kazemi, M.A. (2020) Correlation of Apparent Diffusion Coefficient Values and Peritumoral Edema with Pathologic Biomarkers in Patients with Breast Cancer. Clinical Imaging, 68, 242-248. [Google Scholar] [CrossRef] [PubMed]
[15] Yuan, C., Jin, F., Guo, X., Zhao, S., Li, W. and Guo, H. (2019) Correlation Analysis of Breast Cancer DWI Combined with DCE-MRI Imaging Features with Molecular Subtypes and Prognostic Factors. Journal of Medical Systems, 43, Article No. 83. [Google Scholar] [CrossRef] [PubMed]
[16] Liu, W., Liu, C., Yang, Y., Chen, Y., Muhetaier, A., Lin, Z., et al. (2025) Combining Conventional Magnetic Resonance Imaging Parameters with Clinicopathologic Data for Differentiation of the Three-Tiered Human Epidermal Growth Factor Receptor 2 Status in Breast Cancer. Clinical Radiology, 86, Article 106955. [Google Scholar] [CrossRef] [PubMed]
[17] Guo, H.D., Zhu, J.G., Pylypenko, D., et al. (2024) Ultrafast Dynamic Contrast-Enhanced Breast MRI with Quantitative Perfusion Parameters in Differentiating Breast Cancer: A Study Focusing on Triple-Negative and HER2 Positive Breast Cancer. Frontiers in Oncology, 14, Article 1457918. [Google Scholar] [CrossRef] [PubMed]
[18] Zhan, T., Dai, J. and Li, Y. (2024) Noninvasive Identification of HER2-Zero,-Low, or-Overexpressing Breast Cancers: Multiparametric MRI-Based Quantitative Characterization in Predicting HER2-Low Status of Breast Cancer. European Journal of Radiology, 177, Article 111573. [Google Scholar] [CrossRef] [PubMed]
[19] Chen, X., Li, M. and Su, D. (2024) Machine Learning Models for Differential Diagnosing HER2-Low Breast Cancer: A Radiomics Approach. Medicine, 103, e39343. [Google Scholar] [CrossRef] [PubMed]
[20] Liu, T., Lin, J., Zhang, J., Lou, J., Zou, Q., Wang, S., et al. (2025) The Clinical Value of Radiomics Models Based on Multi-Parameter MRI Features in Evaluating the Different Expression Status of HER2 in Breast Cancer. Acta Radiologica, 66, 597-607. [Google Scholar] [CrossRef] [PubMed]
[21] Ramtohul, T., Djerroudi, L., Lissavalid, E., Nhy, C., Redon, L., Ikni, L., et al. (2023) Multiparametric MRI and Radiomics for the Prediction of HER2-Zero,-Low, and-Positive Breast Cancers. Radiology, 308, e222646. [Google Scholar] [CrossRef] [PubMed]
[22] Li, H., Hou, Y., Xue, L.Y., et al. (2024) Use of MRI Radiomics Models in Evaluating the Low HER2 Expression in Breast Cancer. Current Medical Imaging, 20, e15734056234429.
[23] Peng, Y., Zhang, X., Qiu, Y., Li, B., Yang, Z., Huang, J., et al. (2024) Development and Validation of MRI Radiomics Models to Differentiate HER2-Zero,-Low, and-Positive Breast Cancer. American Journal of Roentgenology, 222, e2330603. [Google Scholar] [CrossRef] [PubMed]
[24] Luo, H.J., Ren, J.L., Mei, G.L., et al. (2024) MRI-Based Machine Learning Radiomics for Prediction of HER2 Expression Status in Breast Invasive Ductal Carcinoma. European Journal of Radiology Open, 13, Article 100592. [Google Scholar] [CrossRef] [PubMed]
[25] Li, X., Fang, J., Wang, F., Zhang, L., Jiang, X. and Mao, X. (2025) Prediction of HER2 Expression in Breast Cancer Patients Based on Multi-Parametric MRI Intratumoral and Peritumoral Radiomics Features Combined with Clinical and Imaging Indicators. Frontiers in Oncology, 15, Article 1531553. [Google Scholar] [CrossRef] [PubMed]
[26] Zhou, J., Yu, X., Wu, Q., Wu, Y., Fu, C., Wang, Y., et al. (2024) Radiomics Analysis of Intratumoral and Different Peritumoral Regions from Multiparametric MRI for Evaluating HER2 Status of Breast Cancer: A Comparative Study. Heliyon, 10, e28722. [Google Scholar] [CrossRef] [PubMed]
[27] Zhan, T., Tang, X., Dai, J., Deng, Y. and Lu, C. (2025) Multiparametric MRI-Based Radiomics Nomogram for Noninvasive Stratification of HER2 Expression Status in Breast Cancer. Quantitative Imaging in Medicine and Surgery, 15, 10215-10237. [Google Scholar] [CrossRef] 
[28] Liu, W., Yang, Y., Wang, X., Li, C., Liu, C., Li, X., et al. (2025) A Comprehensive Model Outperformed the Single Radiomics Model in Noninvasively Predicting the HER2 Status in Patients with Breast Cancer. Academic Radiology, 32, 24-36. [Google Scholar] [CrossRef] [PubMed]
[29] Zhang, L., Zhou, X., Liu, L., Liu, A., Zhao, W., Zhang, H., et al. (2023) Comparison of Dynamic Contrast-Enhanced MRI and Non-Mono-Exponential Model-Based Diffusion-Weighted Imaging for the Prediction of Prognostic Biomarkers and Molecular Subtypes of Breast Cancer Based on Radiomics. Journal of Magnetic Resonance Imaging, 58, 1590-1602. [Google Scholar] [CrossRef] [PubMed]
[30] Dai, Y., Lian, C., Zhang, Z., Gao, J., Lin, F., Li, Z., et al. (2025) Development and Validation of a Deep Learning System to Differentiate HER2‐Zero, HER2‐Low, and HER2‐Positive Breast Cancer Based on Dynamic Contrast‐Enhanced MRI. Journal of Magnetic Resonance Imaging, 61, 2212-2220. [Google Scholar] [CrossRef] [PubMed]
[31] Zhang, X., Shen, Y.Y., Su, G.H., et al. (2025) A Dynamic Contrast‐Enhanced MRI-Based Vision Transformer Model for Distinguishing HER2‐Zero, ‐Low, and ‐Positive Expression in Breast Cancer and Exploring Model Interpretability. Advanced Science, 12, e03925. [Google Scholar] [CrossRef] [PubMed]
[32] Wong, C., Yang, Q., Liang, Y., Wei, Z., Dai, Y., Xu, Z., et al. (2025) AI-Driven MRI Biomarker for Triple-Class HER2 Expression Classification in Breast Cancer: A Large-Scale Multicenter Study. Breast Cancer Research, 27, Article No. 166. [Google Scholar] [CrossRef] 
[33] Lin, Z., Huang, F., Wei, L., Liao, X. and Gao, Y. (2025) Predicting Human Epidermal Growth Factor Receptor 2 Expression in Breast Cancer Based on Radiomics of MRI Habitat and US. Breast Cancer: Targets and Therapy, 17, 711-725. [Google Scholar] [CrossRef] [PubMed]
[34] Wang, Q., Zhang, Z., Huang, C., Xue, H., Zhang, H., Bo, F., et al. (2025) Dual-Modality Virtual Biopsy System Integrating MRI and MG for Noninvasive Predicting HER2 Status in Breast Cancer. Academic Radiology, 32, 3858-3869. [Google Scholar] [CrossRef] [PubMed]
[35] Chen, Y., Chen, S., Tang, W., Kong, Q., Zhong, Z., Yu, X., et al. (2025) Multiparametric MRI Radiomics with Machine Learning for Differentiating HER2-Zero,-Low, and-Positive Breast Cancer: Model Development, Testing, and Interpretability Analysis. American Journal of Roentgenology, 224, e2431717. [Google Scholar] [CrossRef] [PubMed]

为你推荐