Share：
Share this content in WeChat
X
[Chinese] [PDF] 34 1
• Review •
Advances in predicting response to neoadjuvant therapy for hormone receptor-positive breast cancer based on multi-omics integration of DCE-MRI deep learning and tumor microenvironment
GENG Xiping  SUN Yiyao  ZHANG Yong  ZHAO Dan 

DOI:10.12015/issn.1674-8034.2026.02.026.


[Abstract] Hormone receptor-positive (HR+) breast cancer, the most prevalent molecular subtype (70% to 80% of cases), is characterized by significant tumor heterogeneity and treatment resistance mediated by the tumor microenvironment (TME). This heterogeneity and treatment resistance represent the core bottlenecks limiting the improvement of neoadjuvant therapy (NAT) efficacy and the implementation of individualized diagnosis and treatment. Currently, clinical prediction of NAT efficacy relies on methods such as needle biopsy and Ki-67 detection. However, affected by spatiotemporal heterogeneity and indicator fluctuation, these methods cannot accurately evaluate treatment response, creating an urgent need for superior non-invasive predictive tools. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) leverages its functional imaging advantages to quantitatively reflect key TME features, such as tumor angiogenesis and vascular permeability. This provides a crucial means for the non-invasive analysis of TME biological behaviors. Deep learning (DL) technology, by autonomously mining deep spatiotemporal features in DCE-MRI images that exceed human visual recognition, breaks through the limitations of traditional radiomics. It offers a new paradigm for constructing high-precision TME characterization and NAT efficacy prediction models. This article systematically reviews the heterogeneous characteristics of HR+ breast cancer TME, the technical advantages of DCE-MRI in TME functional evaluation, DL-driven imaging feature mining strategies, and research progress in multimodal integration. It focuses on elaborating key technical bottlenecks in this interdisciplinary field. Additionally, it prospects the future research direction based on the integration of "imaging-pathology-molecular" multi-omics. The aim is to provide theoretical references and technical paths for the clinical transformation of precise diagnosis and treatment of HR+ breast cancer.
[Keywords] hormone receptor positive breast cancer；tumor microenvironment；neoadjuvant therapy；dynamic contrast-enhanced magnetic resonance imaging；multi-omics；artificial intelligence；deep learning；magnetic resonance imaging

GENG Xiping1   SUN Yiyao2   ZHANG Yong3   ZHAO Dan4*  

1 Outpatient Department, Liaoning Cancer Hospital, Shenyang 110042, China

2 School of Intelligent Medicine, China Medical University, Shenyang 110122, China

3 Department of Pathology, Liaoning Cancer Hospital, Shenyang 110042, China

4 Department of Medical Imaging, Liaoning Cancer Hospital, Shenyang 110042, China

Corresponding author: ZHAO D, E-mail: zhaodan777@126.com

Conflicts of interest   None.

Received  2025-11-14
Accepted  2026-01-30
DOI: 10.12015/issn.1674-8034.2026.02.026
DOI:10.12015/issn.1674-8034.2026.02.026.

[1]
CHEN L, WU W Y, LIANG F, et al. A prospective, phase II, neoadjuvant study based on chemotherapy sensitivity in HR+/HER2- breast cancer-FINEST study[J]. Cancer Commun, 2025, 45(4): 411-421. DOI: 10.1002/cac2.12649.
[2]
COMES M C, FANIZZI A, BOVE S, et al. Explainable 3D CNN based on baseline breast DCE-MRI to give an early prediction of pathological complete response to neoadjuvant chemotherapy[J/OL]. Comput Biol Med, 2024, 172: 108132 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/38508058/. DOI: 10.1016/j.compbiomed.2024.108132.
[3]
WU C W, WANG L X, WANG N, et al. Prediction of early neoadjuvant chemotherapy response of breast cancer through deep learning-based pharmacokinetic quantification of DCE MRI[J/OL]. Radiol Artif Intell, 2025, 7(5): e240769 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/40631989/. DOI: 10.1148/ryai.240769.
[4]
SHI Z D, BIAN X X, ZHU H Y, et al. Personalized prediction of pathological complete response in breast cancer neoadjuvant therapy: a nomogram combining quantitative MRI biomarkers and molecular subtypes[J/OL]. Front Oncol, 2025, 15: 1669700 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/41079107/. DOI: 10.3389/fonc.2025.1669700.
[5]
ZHANG X Y, TENG X Z, ZHANG J, et al. Enhancing pathological complete response prediction in breast cancer: the role of dynamic characterization of DCE-MRI and its association with tumor heterogeneity[J/OL]. Breast Cancer Res, 2024, 26(1): 77 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/38745321/. DOI: 10.1186/s13058-024-01836-3.
[6]
MA W H, YANG L, ZHANG Y, et al. Heterogeneity assessment of breast cancer tumor microenvironment: multiparametric quantitative analysis with DCE-MRI and discovery of radiomics biomarkers[J/OL]. Breast Cancer, 2025, 17: 573-581 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/40657027/. DOI: 10.2147/BCTT.S530834.
[7]
LI X, HUANG W, HOLMES J H. Dynamic contrast-enhanced (DCE) MRI[J]. Magn Reson Imaging Clin N Am, 2024, 32(1): 47-61. DOI: 10.1016/j.mric.2023.09.001.
[8]
WANG Y, YU W L, LI T, et al. Value of magnetic resonance imaging multiple parameters in the differentiation between olfactory neuroblastoma and sinonasal diffusion large B cell lymphoma[J]. Chin Arch Otolaryngol Head Neck Surg, 2024, 31(7): 426-430. DOI: 10.16066/j.1672-7002.2024.07.004.
[9]
MAYFIELD J D, ATAYA D, ABDALAH M, et al. Presurgical upgrade prediction of DCIS to invasive ductal carcinoma using time-dependent deep learning models with DCE MRI[J/OL]. Radiol Artif Intell, 2024, 6(5): e230348 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/38900042/. DOI: 10.1148/ryai.230348.
[10]
JIANG B T, BAO L L, HE S Q, et al. Deep learning applications in breast cancer histopathological imaging: diagnosis, treatment, and prognosis[J/OL]. Breast Cancer Res, 2024, 26(1): 137 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/39304962/. DOI: 10.1186/s13058-024-01895-6.
[11]
LUO L Y, WANG X, LIN Y, et al. Deep learning in breast cancer imaging: a decade of progress and future directions[J/OL]. IEEE Rev Biomed Eng, 2025, 18: 130-151 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/38265911/. DOI: 10.1109/RBME.2024.3357877.
[12]
YANG Z T, WU H, GAO H Y, et al. Advances in deep learning and radiomics on ovarian cancer[J]. Chin J Magn Reson Imaging, 2025, 16(9): 223-228. DOI: 10.12015/issn.1674-8034.2025.09.034.
[13]
GOLDBERG J, PASTORELLO R G, VALLIUS T, et al. The immunology of hormone receptor positive breast cancer[J/OL]. Front Immunol, 2021, 12: 674192 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/34135901/. DOI: 10.3389/fimmu.2021.674192.
[14]
HERMIDA-PRADO F, XIE Y T, SHERMAN S, et al. Endocrine therapy synergizes with SMAC mimetics to potentiate antigen presentation and tumor regression in hormone receptor-positive breast cancer[J]. Cancer Res, 2023, 83(19): 3284-3304. DOI: 10.1158/0008-5472.CAN-23-1711.
[15]
PENG Y L, XIONG L B, ZHOU Z H, et al. Single-cell transcriptomics reveals a low CD8+ T cell infiltrating state mediated by fibroblasts in recurrent renal cell carcinoma[J/OL]. J Immunother Cancer, 2022, 10(2): e004206 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/35121646/. DOI: 10.1136/jitc-2021-004206.
[16]
XU A Z, AYOUB S, ZHANG H J, et al. Regulatory T cells in invasive breast cancer: prognosis, mechanisms and therapy[J/OL]. Cancers, 2025, 17(19): 3172 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/41097701/. DOI: 10.3390/cancers17193172.
[17]
NISSEN N I, KARSDAL M, WILLUMSEN N. Collagens and Cancer associated fibroblasts in the reactive stroma and its relation to Cancer biology[J/OL]. J Exp Clin Cancer Res, 2019, 38(1): 115 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/30841909/. DOI: 10.1186/s13046-019-1110-6.
[18]
SCHOUTEN S M, LEWIS D, CORNELISSEN S, et al. Dynamic contrast-enhanced and diffusion-weighted MR imaging for predicting tumor growth of sporadic vestibular schwannomas: a prospective study[J]. Neuro Oncol, 2025, 27(4): 1116-1127. DOI: 10.1093/neuonc/noae252.
[19]
HOFFMANN E, GERWING M, KRÄHLING T, et al. Vascular response patterns to targeted therapies in murine breast cancer models with divergent degrees of malignancy[J/OL]. Breast Cancer Res, 2023, 25(1): 56 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/37221619/. DOI: 10.1186/s13058-023-01658-9.
[20]
XIAN M, YU J Q, LI Z, et al. Microvessel barrier dysfunction in sinonasal inverted Papilloma-associated squamous cell carcinoma and its manifestation in dynamic contrast-enhanced MRI[J]. Int Forum Allergy Rhinol, 2024, 14(7): 1173-1181. DOI: 10.1002/alr.23316.
[21]
NOMANI A, YOUSEFI S, SARGSYAN D, et al. A quantitative MRI-based approach to estimate the permeation and retention of nanomedicines in tumors[J/OL]. J Control Release, 2024, 368: 728-739 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/38493951/. DOI: 10.1016/j.jconrel.2024.03.019.
[22]
DU D, LIU X J, LIU Y F, et al. Predictive value of DCE-MRI quantitative parameters for the curative effect of neoadjuvant chemotherapy in breast cancer[J]. Chin J CT MRI, 2025, 23(3): 115-118. DOI: 10.3969/j.issn.1672-5131.2025.03.034.
[23]
STANZIONE A, CUOCOLO R, UGGA L, et al. Oncologic imaging and radiomics: a walkthrough review of methodological challenges[J/OL]. Cancers, 2022, 14(19): 4871 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/36230793/. DOI: 10.3390/cancers14194871.
[24]
ZHOU Y, SHU X, WANG F, et al. Prediction of neoadjuvant therapy response in breast cancer based on interpretable artificial intelligence[J]. Int J Surg, 2026, 112(1): 1066-1080. DOI: 10.1097/js9.0000000000003326.
[25]
ZHANG X, SHEN Y Y, SU G H, et al. A dynamic contrast-enhanced MRI-based vision transformer model for distinguishing HER2-zero, -low, and-positive expression in breast cancer and exploring model interpretability[J/OL]. Adv Sci, 2025, 12(33): e03925 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/40488332/. DOI: 10.1002/advs.202503925.
[26]
ADRADA B E, GUIRGUIS M S, HUO L, et al. Imaging- and tumor biomarker-based multivariable model for early prediction of pathologic complete response to neoadjuvant systemic therapy in triple-negative breast cancer[J/OL]. JCO Precis Oncol, 2025, 9: e2500410 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/41411609/. DOI: 10.1200/PO-25-00410.
[27]
HUANG J H, AO Y S, MU L, et al. Feasibility of ultrafast DCE-MRI for identifying benign and malignant breast lesions[J/OL]. Comput Med Imag Graph, 2025, 123: 102561 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/40300227/. DOI: 10.1016/j.compmedimag.2025.102561.
[28]
ZHAO Z H, DU S Y, XU Z Y, et al. SwinHR: Hemodynamic-powered hierarchical vision transformer for breast tumor segmentation[J/OL]. Comput Biol Med, 2024, 169: 107939 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/38194781/. DOI: 10.1016/j.compbiomed.2024.107939.
[29]
RAMTOHUL T, TESCHER C, VAFLARD P, et al. Prospective evaluation of ultrafast breast MRI for predicting pathologic response after neoadjuvant therapies[J]. Radiology, 2022, 305(3): 565-574. DOI: 10.1148/radiol.220389.
[30]
LIANG Y H, TANG W J, WANG T, et al. HRadNet: a hierarchical radiomics-based network for multicenter breast cancer molecular subtypes prediction[J]. IEEE Trans Med Imaging, 2024, 43(3): 1225-1236. DOI: 10.1109/TMI.2023.3331301.
[31]
ZHANG Y N, LIU L, LI W L, et al. PDGFB-targeted functional MRI nanoswitch for activatable T(1)-T(2) dual-modal ultra-sensitive diagnosis of cancer[J/OL]. J Nanobiotechnology, 2023, 21(1): 9 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/36609374/. DOI: 10.1186/s12951-023-01769-7.
[32]
DAMMU H, REN T, DUONG T Q. Deep learning prediction of pathological complete response, residual cancer burden, and progression-free survival in breast cancer patients[J/OL]. PLoS One, 2023, 18(1): e0280148 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/36607982/. DOI: 10.1371/journal.pone.0280148.
[33]
HAN X R, GUO Y, YE H F, et al. Development of a machine learning-based radiomics signature for estimating breast cancer TME phenotypes and predicting anti-PD-1/PD-L1 immunotherapy response[J/OL]. Breast Cancer Res, 2024, 26(1): 18 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/38287356/. DOI: 10.1186/s13058-024-01776-y.
[34]
YOU C, SU G H, ZHANG X, et al. Multicenter radio-multiomic analysis for predicting breast cancer outcome and unravelling imaging-biological connection[J/OL]. NPJ Precis Oncol, 2024, 8(1): 193 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/39244594/. DOI: 10.1038/s41698-024-00666-y.
[35]
SU G H, XIAO Y, YOU C, et al. Radiogenomic-based multiomic analysis reveals imaging intratumor heterogeneity phenotypes and therapeutic targets[J/OL]. Sci Adv, 2023, 9(40): eadf0837 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/37801493/. DOI: 10.1126/sciadv.adf0837.
[36]
HUANG Y H, SHI Z Y, ZHU T, et al. Longitudinal MRI-driven multi-modality approach for predicting pathological complete response and B cell infiltration in breast cancer[J/OL]. Adv Sci, 2025, 12(12): 2413702 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/39921294/. DOI: 10.1002/advs.202413702.
[37]
HONG M P, CHEN X B, HUANG X W, et al. A macro-micro-macro radiogenomic framework identifies FIBCD1 as a key immune-modulating biomarker in breast cancer[J/OL]. J Transl Med, 2025, 23(1): 1350 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/41291728/. DOI: 10.1186/s12967-025-07389-z.
[38]
LI F L, WEI Y N, ZHANG W C, et al. AI-powered prediction model for neoadjuvant chemotherapy efficacy: comprehensive analysis of breast cancer histological images[J/OL]. NPJ Precis Oncol, 2025, 9(1): 239 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/40664754/. DOI: 10.1038/s41698-025-01033-1.
[39]
LI W, HUANG Y H, ZHU T, et al. Noninvasive artificial intelligence system for early predicting residual cancer burden during neoadjuvant chemotherapy in breast cancer[J]. Ann Surg, 2025, 281(4): 645-654. DOI: 10.1097/SLA.0000000000006279.
[40]
ZHANG L, CUI Q X, ZHOU L Q, et al. MRI-based vector radiomics for predicting breast cancer HER2 status and its changes after neoadjuvant therapy[J/OL]. Comput Med Imaging Graph, 2024, 118: 102443 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/39427545/. DOI: 10.1016/j.compmedimag.2024.102443.
[41]
DU Y H, DING X Y, YE Y Q. The spatial multi-omics revolution in cancer therapy: Precision redefined[J/OL]. Cell Rep Med, 2024, 5(9): 101740 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/39293393/. DOI: 10.1016/j.xcrm.2024.101740.
[42]
FENG X D, SHI Y, WU M, et al. Predicting the efficacy of neoadjuvant chemotherapy in breast cancer patients based on ultrasound longitudinal temporal depth network fusion model[J/OL]. Breast Cancer Res, 2025, 27(1): 30 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/40016785/. DOI: 10.1186/s13058-025-01971-5.
[43]
YU Y F, REN W, HE Z F, et al. Machine learning radiomics of magnetic resonance imaging predicts recurrence-free survival after surgery and correlation of LncRNAs in patients with breast cancer: a multicenter cohort study[J/OL]. Breast Cancer Res, 2023, 25(1): 132 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/37915093/. DOI: 10.1186/s13058-023-01688-3.
[44]
DERCLE L, MCGALE J, ZHAO B S, et al. Artificial intelligence and radiomics biomarkers for treatment response prediction in advanced HER2-negative breast cancer[J/OL]. Breast, 2025, 84: 104571 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/40974664/. DOI: 10.1016/j.breast.2025.104571.
[45]
ZHANG T Y, TAN T, HAN L Y, et al. Predicting breast cancer types on and beyond molecular level in a multi-modal fashion[J/OL]. NPJ Breast Cancer, 2023, 9(1): 16 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/36949047/. DOI: 10.1038/s41523-023-00517-2.
[46]
GUO F Y, SUN S W, DENG X Q, et al. Predicting axillary lymph node metastasis in breast cancer using a multimodal radiomics and deep learning model[J/OL]. Front Immunol, 2024, 15: 1482020 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/39735531/. DOI: 10.3389/fimmu.2024.1482020.
[47]
MAO N, DAI Y, ZHOU H, et al. A multimodal and fully automated system for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer[J/OL]. Sci Adv, 2025, 11(18): eadr1576 [2025-11-13]. https://pubmed.ncbi.nlm.nih.gov/40305609/. DOI: 10.1126/sciadv.adr1576.

PREV Research progress of artificial intelligence in imaging diagnosis of ischemic stroke
NEXT Research progress of magnetic resonance water-fat separation technology in the degree of kidney damage in chronic kidney disease
  


LINK


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