Share:
Share this content in WeChat
X
• Review •
Research advances in multimodal MRI for evaluating the efficacy of neoadjuvant therapy in breast cancer
DING Wenxuan  ZHAO Yiping  ZHANG Xiyou  GUO Zuxin  ZHANG Yang 

DOI:10.12015/issn.1674-8034.2026.11.020.


[Abstract] Among women worldwide, breast cancer is one of the most common malignant tumors, and neoadjuvant therapy (NAT) is one of the core treatment strategies for this disease; however, there are significant individual differences in the incidence of pathological complete response (pCR) following neoadjuvant therapy among patients with different molecular subtypes.Accurate, non-invasive dynamic assessment of treatment efficacy can assist clinicians in promptly adjusting treatment plans and evaluating patient prognosis. Multimodal MRI includes dynamic contrast-enhanced MRI (DCE-MRI), diffusion-weighted imaging (DWI), intravoxel incoherent motion (IVIM), diffusion kurtosis imaging (DKI), and synthetic magnetic resonance imaging (SyMRI). These sequences provide insights into tumor heterogeneity and treatment response from multiple perspectives, including perfusion, cell density, tissue microstructure, and quantitative relaxation properties. With ongoing advancements in the fields of radiomics and deep learning, the in-depth analysis and fusion of multimodal imaging data have been supported, and the accuracy and stability of treatment efficacy prediction models have been optimized. This paper systematically reviews current research progress on the application of multimodal MRI in evaluating the efficacy of NAT for breast cancer. It focuses on summarizing the biological significance and clinical value of functional MRI quantitative parameters, and outlines the technical approaches and existing limitations of using bioinformatics and deep learning for multimodal data integration.Building on this foundation, the paper outlines future research directions, including the standardization of imaging protocols, the conduct of large-scale prospective validation studies, the development of interpretable intelligent models, and the establishment of a multidimensional integrated evaluation system. This paper aims to provide a reference for subsequent research and clinical translation regarding the intelligent and systematic evaluation of the efficacy of neoadjuvant therapy for breast cancer.
[Keywords] breast cancer;neoadjuvant therapy;magnetic resonance imaging;multimodal magnetic resonance imaging;radiomics;deep learning

DING Wenxuan1   ZHAO Yiping1   ZHANG Xiyou1   GUO Zuxin1   ZHANG Yang2*  

1 Department of Radiology, the Second Affiliated Hospital of Dalian Medical University, Dalian 116011, China

2 Breast Surgery Department, the Second Affiliated Hospital of Dalian Medical University, Dalian 116011, China

Corresponding author: ZHANG Y, E-mail: zhangyangzz@126.com

Conflicts of interest   None.

Received  2026-06-13
Accepted  2026-09-20
DOI: 10.12015/issn.1674-8034.2026.11.020
DOI:10.12015/issn.1674-8034.2026.11.020.

[1]
SIEGEL R L, GIAQUINTO A N, JEMAL A. Cancer statistics, 2024[J]. CA A Cancer J Clin, 2024, 74(1): 12-49. DOI: 10.3322/caac.21820.
[2]
GRADISHAR W J, MORAN M S, ABRAHAM J, et al. Breast cancer, version 3.2024, NCCN clinical practice guidelines in oncology[J]. J Natl Compr Canc Netw, 2024, 22(5): 331-357. DOI: 10.6004/jnccn.2024.0035.
[3]
KORDE L A, SOMERFIELD M R, CAREY L A, et al. Neoadjuvant chemotherapy, endocrine therapy, and targeted therapy for breast cancer: ASCO guideline[J]. J Clin Oncol, 2021, 39(13): 1485-1505. DOI: 10.1200/JCO.20.03399.
[4]
SCHMID P, CORTES J, DENT R, et al. Overall survival with pembrolizumab in early-stage triple-negative breast cancer[J]. N Engl J Med, 2024, 391(21): 1981-1991. DOI: 10.1056/NEJMoa2409932.
[5]
VAN DER VOORT A, LOUIS F M, VAN RAMSHORST M S, et al. MRI-guided optimisation of neoadjuvant chemotherapy duration in stage Ⅱ-Ⅲ HER2-positive breast cancer (TRAIN-3): a multicentre, single-arm, phase 2 study[J]. Lancet Oncol, 2024, 25(5): 603-613. DOI: 10.1016/S1470-2045(24)00104-9.
[6]
NETTI S, D'ECCLESIIS O, CORSO F, et al. Methodological issues in radiomics: impact on accuracy of MRI for predicting response to neoadjuvant chemotherapy in breast cancer[J]. Eur Radiol, 2025, 35(7): 4325-4334. DOI: 10.1007/s00330-024-11260-y.
[7]
LAMBIN P, RIOS-VELAZQUEZ E, LEIJENAAR R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI: 10.1016/j.ejca.2011.11.036.
[8]
WITOWSKI J, HEACOCK L, REIG B, et al. Improving breast cancer diagnostics with deep learning for MRI[J/OL]. Sci Transl Med, 2022, 14(664): eabo4802 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/36170446/. DOI: 10.1126/scitranslmed.abo4802.
[9]
LV T X, WU Y Q, WANG Y H, et al. A hybrid hemodynamic knowledge-powered and feature reconstruction-guided scheme for breast cancer segmentation based on DCE-MRI[J/OL]. Med Image Anal, 2022, 82: 102572 [2026-06-12]. https://www.sciencedirect.com/science/article/abs/pii/S1361841522002134via%3Dihub. DOI: 10.1016/j.media.2022.102572.
[10]
WANG M Y, HE S F, WANG C Y, et al. A model based on DCE-MRI perfusion parameters and their change rates combined with immunohistochemistry for predictingearly response to neoadjuvant chemotherapy in breast cancer[J]. Radiol Pract, 2026, 41(7): 787-793. DOI: 10.13609/j.cnki.1000-0313.2026.07.008.
[11]
ARLEDGE C A, ZHAO A H, TOPALOGLU U, et al. Dynamic contrast-enhanced MRI for evaluating breast cancer chemotherapy response using conditional generative adversarial networks[J/OL]. Radiol Imag Cancer, 2026, 8: e250110 [2026-06-12]. https://pubs.rsna.org/doi/10.1148/rycan.250110. DOI: 10.1148/rycan.250110.
[12]
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.
[13]
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 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/40631989/. DOI: 10.1148/ryai.240769.
[14]
KATAOKA M. Ultrafast DCE-MRI as a new tool for treatment response prediction in neoadjuvant chemotherapy of breast cancer[J]. Diagn Interv Imag, 2023, 104(12): 565-566. DOI: 10.1016/j.diii.2023.08.005.
[15]
MENDEZ A M, FANG L K, MERIWETHER C H, et al. Diffusion breast MRI: current standard and emerging techniques[J/OL]. Front Oncol, 2022, 12: 844790 [2026-06-12]. https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.844790/full. DOI: 10.3389/fonc.2022.844790.
[16]
IIMA M, KATAOKA M, HONDA M, et al. Diffusion-weighted MRI for the assessment of molecular prognostic biomarkers in breast cancer[J]. Korean J Radiol, 2024, 25(7): 623-633. DOI: 10.3348/kjr.2023.1188.
[17]
GULLO R L, PARTRIDGE S C, SHIN H J, et al. Update on DWI for breast cancer diagnosis and treatment monitoring[J/OL]. AJR Am J Roentgenol, 2024, 222(1): e2329933 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/37850579/. DOI: 10.2214/AJR.23.29933.
[18]
HOTTAT N A, BADR D A, LECOMTE S, et al. Value of diffusion-weighted MRI in predicting early response to neoadjuvant chemotherapy of breast cancer: comparison between ROI-ADC and whole-lesion-ADC measurements[J]. Eur Radiol, 2022, 32(6): 4067-4078. DOI: 10.1007/s00330-021-08462-z.
[19]
ZHANG Y N, ZHAO R M, DU S Y, et al. Radiomics analysis of contrast-free synthetic MRI and apparent diffusion coefficient for early predicting neoadjuvant chemotherapy response in breast cancer[J/OL]. Eur J Radiol, 2025, 191: 112344 [2026-06-12]. https://www.ejradiology.com/article/S0720-048X(25)00430-9/abstract. DOI: 10.1016/j.ejrad.2025.112344.
[20]
MUSALL B C, ADRADA B E, CANDELARIA R P, et al. Quantitative apparent diffusion coefficients from peritumoral regions as early predictors of response to neoadjuvant systemic therapy in triple-negative breast cancer[J]. J Magn Reson Imag, 2022, 56(6): 1901-1909. DOI: 10.1002/jmri.28219.
[21]
IIMA M, HONDA M, SIGMUND E E, et al. Diffusion MRI of the breast: Current status and future directions[J]. J Magn Reson Imag, 2020, 52(1): 70-90. DOI: 10.1002/jmri.26908.
[22]
HE L T, QIN Y J, HU Q L, et al. Quantitative characterization of breast lesions and normal fibroglandular tissue using compartmentalized diffusion-weighted model: comparison of intravoxel incoherent motion and restriction spectrum imaging[J/OL]. Breast Cancer Res, 2024, 26(1): 71 [2026-06-12]. https://link.springer.com/article/10.1186/s13058-024-01828-3. DOI: 10.1186/s13058-024-01828-3.
[23]
GONG X Q, WANG X X, WANG L, et al. Comparing multi-b-value diffusion MRI models for predicting pathologic complete response to neoadjuvant chemotherapy in breast cancer[J/OL]. Radiology, 2025, 316(1): e242969 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/40693938/. DOI: 10.1148/radiol.242969.
[24]
WANG Y W, WANG Z T, WANG W W, et al. The value of multi-parameter magnetic resonance imaging based on IVIM in predicting the efficacy of neoadjuvant chemotherapy for breast cancer[J]. J Med Imag, 2025, 35(5): 66-71. DOI: 10.20258/j.cnki.1006-9011.2025.05.016.
[25]
ZHANG H, ZHENG Y Y, ZHANG M Z, et al. Breast Cancer: Habitat imaging based on intravoxel incoherent motion for predicting pathologic complete response to neoadjuvant chemotherapy[J]. Med Phys, 2025, 52(6): 3711-3722. DOI: 10.1002/mp.17813.
[26]
SHAN H Y, KE T F, BAO S S, et al. Evaluation of functional magnetic resonance APT and DKI imaging for breast cancer[J/OL]. Cancer Cell Int, 2024, 24(1): 401 [2026-06-12]. https://link.springer.com/article/10.1186/s12935-024-03587-9. DOI: 10.1186/s12935-024-03587-9.
[27]
CHEN X L, LUO Y, XIE Z M, et al. Prediction of neoadjuvant chemotherapy efficacy in breast cancer: integrating multimodal imaging and clinical features[J/OL]. BMC Med Imaging, 2025, 25(1): 118 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/40229675/. DOI: 10.1186/s12880-025-01631-2.
[28]
CHEN Z H, ZHANG M Y, WANG M J, et al. Research progress of synthetic MRI in clinical diseases[J]. Chin J Magn Reson Imaging, 2025, 16(7): 227-234. DOI: 10.12015/issn.1674-8034.2025.07.036.
[29]
WANG Y N, SONG D. Application of MRI quantitative analysis technology based on relaxation time in diagnosis and condition evaluation of breast lesions[J]. Chin J Public Health Eng, 2024, 23(6): 802-804.
[30]
ZHAO R M, DU S Y, GAO S, et al. Time course changes of synthetic relaxation time during neoadjuvant chemotherapy in breast cancer: the optimal parameter for treatment response evaluation[J]. J Magn Reson Imaging, 2023, 58(4): 1290-1302. DOI: 10.1002/jmri.28597.
[31]
ZHAN T, YI C H, LANG Y Y. Predicting efficacy of neoadjuvant chemotherapy in breast cancer patients with synthetic magnetic resonance imaging method MAGiC: an observational cohort study[J/OL]. Eur J Radiol, 2024, 179: 111666 [2026-06-12]. https://www.ejradiology.com/article/S0720-048X(24)00382-6/abstract. DOI: 10.1016/j.ejrad.2024.111666.
[32]
ZHANG X Y, DING Y Y, LI Z L, et al. The value of synthetic MRI quantitative parameters in the peritumoral region for evaluating the efficacy of neoadjuvant chemotherapy in breast cancer[J]. J Clin Radiol, 2025, 44(6): 1010-1014.
[33]
WU H H, HUANG Z B, WANG J. Neoadjuvant chemotherapy efficacy in breast cancer: insights from magnetic resonance imaging compilation (MAGIC)[J]. Acad Radiol, 2025, 32(8): 4369-4381. DOI: 10.1016/j.acra.2025.04.020.
[34]
HWANG K P, ELSHAFEEY N A, KOTROTSOU A, et al. A radiomics model based on synthetic MRI acquisition for predicting neoadjuvant systemic treatment response in triple-negative breast cancer[J/OL]. Radiol Imaging Cancer, 2023, 5(4): e230009 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/37505106/. DOI: 10.1148/rycan.230009.
[35]
JOO S, KO E S, KWON S, et al. Multimodal deep learning models for the prediction of pathologic response to neoadjuvant chemotherapy in breast cancer[J/OL]. Sci Rep, 2021, 11: 18800 [2026-06-12]. https://www.nature.com/articles/s41598-021-98408-8. DOI: 10.1038/s41598-021-98408-8.
[36]
LIN R C, HE Z F, HAN J J, et al. A foundation model for predicting outcomes of neoadjuvant chemotherapy in breast cancer[J]. Int J Surg, 2026, 112(2): 2225-2242. DOI: 10.1097/js9.0000000000003999.
[37]
HUANG Y, WANG X X, CAO Y, et al. Nomogram for predicting neoadjuvant chemotherapy response in breast cancer using MRI-based intratumoral heterogeneity quantification[J/OL]. Radiology, 2025, 315(1): e241805 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/40232145/. DOI: 10.1148/radiol.241805.
[38]
BURSTEIN H J, CURIGLIANO G, GNANT M, et al. Tailoring treatment to cancer risk and patient preference: the 2025 St Gallen International Breast Cancer Consensus Statement on individualizing therapy for patients with early breast cancer[J]. Ann Oncol, 2025, 36(12): 1433-1446. DOI: 10.1016/j.annonc.2025.09.007.
[39]
WANG X X, BA R C, HUANG Y, et al. Time-dependent diffusion MRI helps predict molecular subtypes and treatment response to neoadjuvant chemotherapy in breast cancer[J/OL]. Radiology, 2024, 313(1): e240288 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/39436292/. DOI: 10.1148/radiol.240288.
[40]
LOUIS F M, VAN DER VOORT A, VAN RAMSHORST M S, et al. MRI-based personalisation of neoadjuvant chemotherapy duration in HER2-positive early breast cancer (TRAIN-3): primary results from a multicentre, single-arm, phase 2 study[J]. Lancet Oncol, 2026, 27(3): 349-360. DOI: 10.1016/S1470-2045(25)00707-7.
[41]
KAPLAN E, ALAKUS H, KAPLAN S. Pre-treatment breast MRI features and ADC values as predictors of pathologic complete response in breast cancer: a molecular subtype-based analysis[J/OL]. Diagnostics, 2026, 16(6): 938 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/41897671/. DOI: 10.3390/diagnostics16060938.
[42]
WU C Y, JARRETT A M, ZHOU Z J, et al. MRI-based digital models forecast patient-specific treatment responses to neoadjuvant chemotherapy in triple-negative breast cancer[J/OL]. Cancer Res, 2022, 82(18): CAN-C22-1329 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/35914239/. DOI: 10.1158/0008-5472.CAN-22-1329.
[43]
YU Y F, HE Z F, OUYANG J, et al. Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: a machine learning, multicenter study[J/OL]. EBioMedicine, 2021, 69: 103460 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/34233259/. DOI: 10.1016/j.ebiom.2021.103460.
[44]
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 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/37526540/. DOI: 10.1148/radiol.222646.
[45]
SHI Z W, HUANG X M, CHENG Z L, et al. MRI-based quantification of intratumoral heterogeneity for predicting treatment response to neoadjuvant chemotherapy in breast cancer[J/OL]. Radiology, 2023, 308(1): e222830 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/37432083/. DOI: 10.1148/radiol.222830.
[46]
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 [2026-06-12]. https://advanced.onlinelibrary.wiley.com/doi/10.1002/advs.202413702. DOI: 10.1002/advs.202413702.
[47]
RAMTOHUL T, LOLLIVIER D, SPRIET J, et al. Posttreatment MRI to predict pathologic complete response of triple-negative breast cancer to neoadjuvant chemoimmunotherapy[J/OL]. Radiology, 2025, 316(1): e243824 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/40590696/. DOI: 10.1148/radiol.243824.
[48]
CHEN Y L, QIN Y, YANG M, et al. The role of radiomics in predicting the response to neoadjuvant chemotherapy for breast cancer[J]. Cancer Biol Med, 2026, 23(3): 343-362. DOI: 10.20892/j.issn.2095-3941.2025.0655.
[49]
CHEN X X, WANG X M, ZHANG K, et al. Recent advances and clinical applications of deep learning in medical image analysis[J/OL]. Med Image Anal, 2022, 79: 102444 [2026-06-12]. https://www.sciencedirect.com/science/article/abs/pii/S1361841522000913via%3Dihub. DOI: 10.1016/j.media.2022.102444.
[50]
KUMARI S, SINGH P. Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives[J/OL]. Comput Biol Med, 2024, 170: 107912 [2026-06-12]. https://www.sciencedirect.com/science/article/pii/S001048252301377Xvia%3Dihub. DOI: 10.1016/j.compbiomed.2023.107912.
[51]
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 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/40305609/. DOI: 10.1126/sciadv.adr1576.
[52]
ZHANG J D, LI Y H, LI Z R, et al. Deep-learning-based HER2 status assessment from multimodal breast cancer data predicts neoadjuvant therapy response[J]. Nat Biomed Eng, 2026, 10(6): 1235-1246. DOI: 10.1038/s41551-025-01495-5.
[53]
HUANG Y H, ZHU T, ZHANG X L, et al. Longitudinal MRI-based fusion novel model predicts pathological complete response in breast cancer treated with neoadjuvant chemotherapy: a multicenter, retrospective study[J/OL]. EClinicalMedicine, 2023, 58: 101899 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/37007742/. DOI: 10.1016/j.eclinm.2023.101899.
[54]
ZHANG S, SHI Z H, DU S Y, et al. Integration of longitudinal MRI and biopsy whole slide images for early prediction of neoadjuvant therapy response and personalized management in breast cancer: a multicenter retrospective and prospective study[J/OL]. Cancer Lett, 2026, 650: 218508 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/41985873/. DOI: 10.1016/j.canlet.2026.218508.
[55]
GAO Y, VENTURA-DIAZ S, WANG X, et al. An explainable longitudinal multi-modal fusion model for predicting neoadjuvant therapy response in women with breast cancer[J/OL]. Nat Commun, 2024, 15: 9613 [2026-06-12]. https://www.nature.com/articles/s41467-024-53450-8. DOI: 10.1038/s41467-024-53450-8.
[56]
HUANG Y H, SONG X Y, CHEN Y L, et al. Intratumoral microbiome-related MRI model for predicting breast cancer shrinkage pattern following neoadjuvant therapy[J/OL]. Radiology, 2025, 316(2): e243545 [2026-06-12]. https://pubmed.ncbi.nlm.nih.gov/40892452/. DOI: 10.1148/radiol.243545.

PREV Research progress of coronary magnetic resonance angiography
NEXT Research progress on the Kaiser score in breast MRI diagnosis
  



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