Share：
Share this content in WeChat
X
[Chinese] [PDF] 10 1
• Review •
Research progress in using radiomics to predict tumor infiltrating lymphocytes in breast cancer
ZHANG Qiyue  YAN Deyue  LU Xiaoman  CHEN Mingming  SONG Peiji  OUYANG Aimei 

DOI:10.12015/issn.1674-8034.2025.12.030.


[Abstract] Breast cancer, one of the most common malignant tumors affecting women worldwide, poses a serious threat to patients' physical and mental health. Tumor-infiltrating lymphocytes (TILs) play a critical role in the diagnosis and treatment of breast cancer, with their levels closely associated with patients' sensitivity to immunotherapy and prognosis. However, traditional pathological assessment of TILs has several drawbacks, including subjectivity, time-consuming procedures, and the need for invasive biopsies. Emerging radiomics technology extracts quantitative features from medical images and combines them with machine learning models to achieve non-invasive prediction of TILs. This effectively overcomes the limitations of traditional methods, provides an innovative approach for the precise diagnosis and treatment of breast cancer, and holds significant clinical application value. This study reviews literature from PubMed and the China National Knowledge Infrastructure (CNKI) on radiomics-based prediction of TILs in breast cancer. It systematically summarizes key aspects including imaging modality selection and research trends, critically analyzes current limitations in the field, and proposes promising directions for future research. The review aims to provide valuable radiological insights for predicting TILs in breast cancer, facilitate non-invasive assessment of TIL levels, and advance the development of precision medicine.
[Keywords] radiomics；breast cancer；immune microenvironment；tumor-infiltrating lymphocytes；magnetic resonance imaging

ZHANG Qiyue1, 2   YAN Deyue2   LU Xiaoman3   CHEN Mingming3   SONG Peiji2   OUYANG Aimei2*  

1 Graduate Department, Shandong First Medical University (Shandong Academy of Medical Sciences), Jinan 250117, China

2 Department of Radiology, Central Hospital Affiliated to Shandong First Medical University, Jinan 250013, China

3 School of Medical Imaging, Shandong Second Medical University, Weifang 261053, China

Corresponding author: OUYANG A M, E-mail: 13370582510@163.com

Conflicts of interest   None.

Received  2025-08-01
Accepted  2025-11-29
DOI: 10.12015/issn.1674-8034.2025.12.030
DOI:10.12015/issn.1674-8034.2025.12.030.

[1]
JIA T T, LV Q F, ZHANG B, et al. Assessment of androgen receptor expression in breast cancer patients using 18 F-FDG PET/CT radiomics and clinicopathological characteristics[J/OL]. BMC Med Imaging, 2023, 23(1): 93 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/37460990/. DOI: 10.1186/s12880-023-01052-z.
[2]
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 (Weinh), 2025, 12(12): e2413702 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/39921294/. DOI: 10.1002/advs.202413702.
[3]
MA H D, SHI L L, ZHENG J Y, et al. Advanced machine learning unveils CD8 + T cell genetic markers enhancing prognosis and immunotherapy efficacy in breast cancer[J/OL]. BMC Cancer, 2024, 24(1): 1222 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/39354417/. DOI: 10.1186/s12885-024-12952-w.
[4]
LECLERC M, VOILIN E, GROS G, et al. Regulation of antitumour CD8 T-cell immunity and checkpoint blockade immunotherapy by Neuropilin-1[J/OL]. Nat Commun, 2019, 10(1): 3345 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/31350404/. DOI: 10.1038/s41467-019-11280-z.
[5]
STANTON S E, DISIS M L. Clinical significance of tumor-infiltrating lymphocytes in breast cancer[J/OL]. J Immunother Cancer, 2016, 4: 59 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/27777769/. DOI: 10.1186/s40425-016-0165-6.
[6]
SALGADO R, DENKERT C, DEMARIA S, et al. The evaluation of tumor-infiltrating lymphocytes (TILs) in breast cancer: recommendations by an International TILs Working Group 2014[J]. Ann Oncol, 2015, 26(2): 259-271. DOI: 10.1093/annonc/mdu450.
[7]
CHEN S, SUI Y, DING S, et al. A simple and convenient model combining multiparametric MRI and clinical features to predict tumour-infiltrating lymphocytes in breast cancer[J/OL]. Clin Radiol, 2023, 78(12): e1065-e1074 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/37813758/. DOI: 10.1016/j.crad.2023.08.029.
[8]
LIU Z W, LUO C, CHEN X J, et al. Noninvasive prediction of perineural invasion in intrahepatic cholangiocarcinoma by clinicoradiological features and computed tomography radiomics based on interpretable machine learning: a multicenter cohort study[J]. Int J Surg, 2024, 110(2): 1039-1051. DOI: 10.1097/JS9.0000000000000881.
[9]
LIU K M, SUN X L, ZHANG H X, et al. Construction and validation of a predictive model for HER-2 expression status in breast cancer based on intratumoral multiparametric MRI[J]. J Clin Radiol, 2025, 44(8): 1414-1420. DOI: 10.13437/j.cnki.jcr.2025.08.032.
[10]
ZHANG H X, NIU S X, CHEN H H, et al. Radiomics signatures for predicting the Ki-67 level and HER-2 status based on bone metastasis from primary breast cancer[J/OL]. Front Cell Dev Biol, 2024, 11: 1220320 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/38264355/. DOI: 10.3389/fcell.2023.1220320.
[11]
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 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/37007742/. DOI: 10.1016/j.eclinm.2023.101899.
[12]
ZHAO J L, SUN Z X, YU Y F, et al. Radiomic and clinical data integration using machine learning predict the efficacy of anti-PD-1 antibodies-based combinational treatment in advanced breast cancer: a multicentered study[J/OL]. J Immunother Cancer, 2023, 11(5): e006514 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/37217246/. DOI: 10.1136/jitc-2022-006514.
[13]
YANG X W, LI J, SUN H, et al. Radiomics integration of mammography and DCE-MRI for predicting molecular subtypes in breast cancer patients[J/OL]. Breast Cancer (Dove Med Press), 2025, 17: 187-200 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/39990966/. DOI: 10.2147/BCTT.S488200.
[14]
WU J, LI Y X, GONG W Q, et al. Multi-modality radiomics diagnosis of breast cancer based on MRI, ultrasound and mammography[J/OL]. BMC Med Imaging, 2025, 25(1): 265 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/40615781/. DOI: 10.1186/s12880-025-01767-1.
[15]
ZHANG H, MIAO Q, FU Y, et al. Intratumoral and peritumoral radiomics based on automated breast volume scanner for predicting human epidermal growth factor receptor 2 status[J/OL]. Front Oncol, 2025, 15: 1556317 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/40308512/. DOI: 10.3389/fonc.2025.1556317.
[16]
HAN Y X, HUANG M X, XIE L Z, et al. The value of intratumoral and peritumoral radiomics features based on multiparametric MRI for predicting molecular staging of breast cancer[J/OL]. Front Oncol, 2025, 15: 1379048 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/40134601/. DOI: 10.3389/fonc.2025.1379048.
[17]
HU Y L, CAI Z H, AIERKEN N, et al. Intra- and peri-tumoral radiomics based on dynamic contrast-enhanced MRI for prediction of benign disease in BI-RADS 4 breast lesions: a multicentre study[J/OL]. Radiat Oncol, 2025, 20(1): 27 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/40022114/. DOI: 10.1186/s13014-025-02605-y.
[18]
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 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/38287356/. DOI: 10.1186/s13058-024-01776-y.
[19]
JEON S H, KIM S W, NA K, et al. Radiomic models based on magnetic resonance imaging predict the spatial distribution of CD8+ tumor-infiltrating lymphocytes in breast cancer[J/OL]. Front Immunol, 2022, 13: 1080048 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/36601118/. DOI: 10.3389/fimmu.2022.1080048.
[20]
YANG B, ZHOU L, ZHONG J, et al. Combination of computed tomography imaging-based radiomics and clinicopathological characteristics for predicting the clinical benefits of immune checkpoint inhibitors in lung cancer[J/OL]. Respir Res, 2021, 22(1): 189 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/34183009/. DOI: 10.1186/s12931-021-01780-2.
[21]
LIU B Y, GU X R, XIE D L, et al. An ultrasound-based machine learning model for predicting tumor-infiltrating lymphocytes in breast cancer[J/OL]. Technol Cancer Res Treat, 2025, 24: 15330338251334453 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/40241518/. DOI: 10.1177/15330338251334453.
[22]
ZHAO X M, WANG M D, WEI Y C, et al. Overview of multimodal radiomics and deep learning in the prediction of axillary lymph node status in breast cancer[J]. Acad Radiol, 2025, 32(11): 6623-6641. DOI: 10.1016/j.acra.2025.07.017.
[23]
ZHANG M, LI X Y, ZHOU P, et al. Prediction value study of breast cancer tumor infiltrating lymphocyte levels based on ultrasound imaging radiomics[J/OL]. Front Oncol, 2024, 14: 1411261 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/38903726/. DOI: 10.3389/fonc.2024.1411261.
[24]
LI Y, CHEN C M, LI W W, et al. Radiomic features based on pyradiomics predict CD276 expression associated with breast cancer prognosis[J/OL]. Heliyon, 2024, 10(17): e37345 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/39296227/. DOI: 10.1016/j.heliyon.2024.e37345.
[25]
LI X G, DONG Q J, CONG C, et al. MRI-based radiomics nomogram for predicting CD8-positive tumor-infiltrating lymphocytes levels in HER2-positive breast cancer[J/OL]. Front Oncol, 2025, 15: 1612631 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/41142610/. DOI: 10.3389/fonc.2025.1612631.
[26]
PENG Y, HU X G, LIU Y L, et al. The feasibility of the radiomics models for tumor-infiltrating lymphocytes level prediction in breast cancer based on dynamic contrast-enhanced MRI[J/OL]. BMC Med Imaging, 2025, 25(1): 420 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/41120945/. DOI: 10.1186/s12880-025-01968-8.
[27]
SU G H, XIAO Y, JIANG L, et al. Radiomics features for assessing tumor-infiltrating lymphocytes correlate with molecular traits of triple-negative breast cancer[J/OL]. J Transl Med, 2022, 20(1): 471 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/36243806/. DOI: 10.1186/s12967-022-03688-x.
[28]
BIAN T T, WU Z J, LIN Q, et al. Evaluating tumor-infiltrating lymphocytes in breast cancer using preoperative MRI-based radiomics[J]. J Magn Reson Imaging, 2022, 55(3): 772-784. DOI: 10.1002/jmri.27910.
[29]
JIANG W Y, WU R X, YANG T, et al. Profiling regulatory T lymphocytes within the tumor microenvironment of breast cancer via radiomics[J]. Cancer Med, 2023, 12(24): 21861-21872. DOI: 10.1002/cam4.6757.
[30]
LIANG Y W, XU H N, LIN J, et al. Multi-modal radiomics model based on four imaging modalities for predicting pathological complete response to neoadjuvant treatment in breast cancer[J/OL]. BMC Cancer, 2025, 25(1): 985 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/40457214/. DOI: 10.1186/s12885-025-14407-2.
[31]
YU H W, MENG X Q, CHEN H, et al. Correlation between mammographic radiomics features and the level of tumor-infiltrating lymphocytes in patients with triple-negative breast cancer[J/OL]. Front Oncol, 2020, 10: 412 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/32351879/. DOI: 10.3389/fonc.2020.00412.
[32]
YU H W, MENG X Q, CHEN H, et al. Predicting the level of tumor-infiltrating lymphocytes in patients with breast cancer: usefulness of mammographic radiomics features[J/OL]. Front Oncol, 2021, 11: 628577 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/33777776/. DOI: 10.3389/fonc.2021.628577.
[33]
DAI T, YANG H Y, ZHAO Q, et al. Correlation between cone-beam enhanced CT imaging features with hormone receptor and HER-2 expression in breast cancer[J]. Radiol Pract, 2023, 38(12): 1554-1561. DOI: 10.13609/j.cnki.1000-0313.2023.12.010.
[34]
LI Y, CUI S J, YANG F, et al. Enhanced CT-based radiomcis model can predict tumour-infiltrating lymphocyte levels in breast cancer patients[J]. Imag Sci Photochem, 2024, 42(2): 148-154. DOI: 10.7517/issn.1674-0475.231107.
[35]
AOOTAPHAO S, PUTTAWIBUL P, THAJCHAYAPONG P, et al. Artifact suppression for breast specimen imaging in micro CBCT using deep learning[J/OL]. BMC Med Imaging, 2024, 24(1): 34 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/38321390/. DOI: 10.1186/s12880-024-01216-5.
[36]
YU H T, LI Q, WU S S, et al. Research progress of radiomics based on MRI for prediction of axillary lymph node metastasis in breast cancer[J]. Chin J Magn Reson Imag, 2023, 14(7): 176-180. DOI: 10.12015/issn.1674-8034.2023.07.032.
[37]
BAI Y N, ZHOU R Y, NING Z R, et al. Research progress of MRI radiomics in the efficacy evaluation and prognosis of neoadjuvant therapy for breast cancer[J]. Chin J Magn Reson Imag, 2024, 15(6): 207-211, 223. DOI: 10.12015/issn.1674-8034.2024.06.033.
[38]
FANG C Y, ZHANG J T, LI J Z, 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.
[39]
XU N N, ZHOU J J, HE X X, et al. Radiomics model for evaluating the level of tumor-infiltrating lymphocytes in breast cancer based on dynamic contrast-enhanced MRI[J]. Clin Breast Cancer, 2021, 21(5): 440-449.e1. DOI: 10.1016/j.clbc.2020.12.008.
[40]
TANG W J, KONG Q C, CHENG Z X, et al. Performance of radiomics models for tumour-infiltrating lymphocyte (TIL) prediction in breast cancer: the role of the dynamic contrast-enhanced (DCE) MRI phase[J]. Eur Radiol, 2022, 32(2): 864-875. DOI: 10.1007/s00330-021-08173-5.
[41]
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.
[42]
TANG P, ZHANG Q, MENG L C, et al. Predicting the axillary lymph node tumor burden in breast cancer patients using ultrasonic radiomics nomogram model[J/OL]. PLoS One, 2025, 20(10): e0333172 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/41056243/. DOI: 10.1371/journal.pone.0333172.
[43]
FRANKOWSKA K, ZAROBKIEWICZ M, DĄBROWSKA I, et al. Tumor infiltrating lymphocytes and radiological picture of the tumor[J/OL]. Med Oncol, 2023, 40(6): 176 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/37178270/https://pubmed.ncbi.nlm.nih.gov/37178270/. DOI: 10.1007/s12032-023-02036-3.
[44]
CANDELARIA R P, SPAK D A, RAUCH G M, et al. BI-RADS ultrasound lexicon descriptors and stromal tumor-infiltrating lymphocytes in triple-negative breast cancer[J/OL]. Acad Radiol, 2022, 29(Suppl 1): S35-S41 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/34272161/. DOI: 10.1016/j.acra.2021.06.007.
[45]
HU L, JIN P L, XU W, et al. Clinical and radiomics integrated nomogram for preoperative prediction of tumor-infiltrating lymphocytes in patients with triple-negative breast cancer[J/OL]. Front Oncol, 2024, 14: 1370466 [2025-07-30]. https://pubmed.ncbi.nlm.nih.gov/38567151/. DOI: 10.3389/fonc.2024.1370466.
[46]
TENGHUI W, XINYI L, ZIYI S, et al. Combination of ultrasound-based radiomics and deep learning with clinical data to predict response in breast cancer patients treated with neoadjuvant chemotherapy[J/OL]. Front Oncol, 2025, 15 [2025-07-18]. https://www.frontiersin.org/articles/10.3389/fonc.2025.1525285/full. DOI: 10.3389/fonc.2025.1525285.
[47]
ZHOU L Q, WU X L, HUANG S Y, et al. Lymph node metastasis prediction from primary breast cancer US images using deep learning[J]. Radiology, 2020, 294(1): 19-28. DOI: 10.1148/radiol.2019190372.
[48]
LIU B Q, LIU S Y, CAO Z J, et al. Accurate classification of benign and malignant breast tumors in ultrasound imaging with an enhanced deep learning model[J/OL]. Front Bioeng Biotechnol, 2025, 13: 1526260 [2025-07-18]. https://pubmed.ncbi.nlm.nih.gov/40635689/. DOI: 10.3389/fbioe.2025.1526260.
[49]
ZHI S G, CAI X X, ZHOU W, et al. Application value of deep learning-based AI model in the classification of breast nodules[J]. Br J Hosp Med (Lond), 2025, 86(6): 1-19. DOI: 10.12968/hmed.2025.0078.
[50]
JIA Y Y, WU R C, LU X Y, et al. Deep learning with transformer or convolutional neural network in the assessment of tumor-infiltrating lymphocytes (TILs) in breast cancer based on US images: a dual-center retrospective study[J/OL]. Cancers (Basel), 2023, 15(3): 838 [2025-07-18]. https://pubmed.ncbi.nlm.nih.gov/36765796/. DOI: 10.3390/cancers15030838.
[51]
ZHOU W P, YANG Q, ZHANG H M. Enhanced value of chest computed tomography radiomics features in breast density classification[J/OL]. Sci Rep, 2025, 15(1): 29367 [2025-07-18]. https://pubmed.ncbi.nlm.nih.gov/40954156/. DOI: 10.1038/s41598-025-14190-x.
[52]
PENG Q, JI Z Y, XU N, et al. Prediction of neoadjuvant chemotherapy efficacy in patients with HER2-low breast cancer based on ultrasound radiomics[J/OL]. Cancer Imaging, 2025, 25(1): 112 [2025-07-18]. https://pubmed.ncbi.nlm.nih.gov/41013799/. DOI: 10.1186/s40644-025-00934-5.

PREV Research progress of synthetic MRI in clinical application of head and neck diseases
NEXT Advances in predicting HER-2 expression status in breast cancer using magnetic resonance imaging
  


LINK


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