Share：
Share this content in WeChat
X
[Chinese][PDF]111
• Clinical Article •
Value of radiomics model based on DCE-MRI combined with blood cell parameters in differentiating Luminal and Non-Luminal breast cancer
XU Hao  YANG Ao  HU Yuntao  ZHOU Peng  DENG Heping 

Cite this article as: XU H, YANG A, HU Y T, et al. Value of radiomics model based on DCE-MRI combined with blood cell parameters in differentiating Luminal and Non-Luminal breast cancer[J]. Chin J Magn Reson Imaging, 2025, 16(4): 33-40, 150. DOI:10.12015/issn.1674-8034.2025.04.006.


[Abstract] Objective To explore the value of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics model combined with blood cell parameters in differentiating Luminal and Non-Luminal breast cancer (BC).Materials and Methods DCE-MRI of two hundred and twenty-seven patients with pathologically confirmed BC were retrospectively analyzed. The patients were randomly split into a training set (n = 162) and a validation set (n = 65) at a ratio of 7∶3. Patients were divided into the Luminal group (139 cases) and the Non-Luminal group (88 cases) according to the immunohistochemical results. The BC lesions on the pretreatment DCE-MRI served as the basis for the volume of interest for feature extraction. Three models were constructed to differentiate Luminal from Non-Luminal by analyzing radiomic feature, clinical pathological feature, and hematological parameters. These models were Model 1 (radiomics), Model 2 (hematological parameters), and Model 3 (radiomics + hematological parameters), respectively. The discrimination performance of the models was evaluated using the receiver operating characteristic curve. Decision curve analysis was conducted to determine the clinical usefulness of the models by quantifying the net benefits at different threshold probabilities.Results The area under the curve (AUC), sensitivity, and specificity, of Model 3 were 0.840 (0.774 to 0.893), 87.9%, and 71.4% in the training set, and 0.818 (0.703 to 0.903), 87.5%, and 68.0% in the validation set, respectively. The AUC of the Model 1 was better than that of the Model 2 in the both cohorts (0.817 vs. 0.636, 0.838 vs. 0.515, P = 0.001 and P < 0.001), and the AUC of the Model 3 was also better than that of the Model 2 in the both cohorts (0.840 vs. 0.636, 0.818 vs. 0.515, both P < 0.001). The Model 3 and Model 1 were both more beneficial than Model 2 in clinical practice, as illustrated by decision curve analysis.Conclusions The model that integrated the hematological parameters with DCE-MRI radiomics can help differentiate Luminal from Non-Luminal BC, which facilitates the accurate treatment planning for BC.
[Keywords] Luminal breast cancer；Non-Luminal breast cancer；magnetic resonance imaging；radiomics；hematological parameters；diagnostic value

XU Hao1   YANG Ao1, 2   HU Yuntao1   ZHOU Peng1   DENG Heping1*  

1 Department of Radiology, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic Science and Technology of China, Chengdu 610041, China

2 School of Medicine, University of Electronic Science and Technology of China, Sichuan Cancer Hospital & Institute, Chengdu 610041, China

Corresponding author: DENG H P, E-mail: dengheping1@126.com

Conflicts of interest   None.

Received  2025-01-07
Accepted  2025-04-10
DOI: 10.12015/issn.1674-8034.2025.04.006
Cite this article as: XU H, YANG A, HU Y T, et al. Value of radiomics model based on DCE-MRI combined with blood cell parameters in differentiating Luminal and Non-Luminal breast cancer[J]. Chin J Magn Reson Imaging, 2025, 16(4): 33-40, 150. DOI:10.12015/issn.1674-8034.2025.04.006.

[1]
PHD H S, JACQUES FERLAY MSC M, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA A Cancer J Clin, 2021, 71(3): 209-249. DOI: 10.3322/caac.21660.
[2]
FIDLER M M, GUPTA S, SOERJOMATARAM I, et al. Cancer incidence and mortality among young adults aged 20-39 years worldwide in 2012: a population-based study[J]. Lancet Oncol, 2017, 18(12): 1579-1589. DOI: 10.1016/S1470-2045(17)30677-0.
[3]
GOLDHIRSCH A, WOOD W C, COATES A S, et al. Strategies for subtypes: dealing with the diversity of breast cancer: highlights of the St. Gallen international expert consensus on the primary therapy of early breast cancer 2011[J]. Ann Oncol, 2011, 22(8): 1736-1747. DOI: 10.1093/annonc/mdr304.
[4]
PRAT A, PINEDA E, ADAMO B, et al. Clinical implications of the intrinsic molecular subtypes of breast cancer[J/OL]. Breast, 2015, 24(Suppl 2): S26-S35 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/26253814/. DOI: 10.1016/j.breast.2015.07.008.
[5]
PELLEGRINO B, HLAVATA Z, MIGALI C, et al. Luminal breast cancer: risk of recurrence and tumor-associated immune suppression[J]. Mol Diagn Ther, 2021, 25(4): 409-424. DOI: 10.1007/s40291-021-00525-7.
[6]
GOLDNER M, PANDOLFI N, MACIEL D, et al. Combined endocrine and targeted therapy in luminal breast cancer[J]. Expert Rev Anticancer Ther, 2021, 21(11): 1237-1251. DOI: 10.1080/14737140.2021.1960160.
[7]
BIANCHINI G, DE ANGELIS C, LICATA L, et al. Treatment landscape of triple-negative breast cancer: expanded options, evolving needs[J/OL]. Nat Rev Clin Oncol, 2022, 19: 91-113 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/34754128/. DOI: 10.1038/s41571-021-00565-2.
[8]
YIN Y, ZHANG Y, LI L, et al. Prognostic value of pretreatment lymphocyte-to-monocyte ratio and development of a nomogram in breast cancer patients[J/OL]. Front Oncol, 2021, 11: 650980 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/34976782/. DOI: 10.3389/fonc.2021.650980.
[9]
CHEN X B, CAI Q D, DENG L, et al. Association of inflammatory blood markers and pathological complete response in HER2-positive breast cancer: a retrospective single-center cohort study[J/OL]. Front Immunol, 2024, 15: 1465862 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/39628488/. DOI: 10.3389/fimmu.2024.1465862.
[10]
KAYTAZ TEKYOL K, GURLEYIK G, AKTAŞ A, et al. Pathological complete response to neoadjuvant chemotherapy in patients with breast cancer: the relationship between inflammatory biomarkers and molecular subtypes[J/OL]. Cureus, 2021, 13(4): e14774 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/34094739/. DOI: 10.7759/cureus.14774.
[11]
CAMILLI M, IANNACCONE G, VECCHIA G L, et al. Platelets: the point of interconnection among cancer, inflammation and cardiovascular diseases[J]. Expert Rev Hematol, 2021, 14(6): 537-546. DOI: 10.1080/17474086.2021.1943353.
[12]
CANTRELL R, PALUMBO J S. The thrombin-inflammation axis in cancer progression[J]. Thromb Res, 2020, 191(Suppl 1): S117-S122. DOI: 10.1016/S0049-3848(20)30408-4.
[13]
LAMBIN P, LEIJENAAR R T H, DEIST T M, et al. Radiomics: the bridge between medical imaging and personalized medicine[J]. Nat Rev Clin Oncol, 2017, 14(12): 749-762. DOI: 10.1038/nrclinonc.2017.141.
[14]
ZHANG D Y, HUANG X H, SHEN M Y, et al. Value of MRI radiomics in predicting molecular subtypes of invasive breast carcinoma of no special type[J]. Chin J Magn Reson Imag, 2024, 15(3): 100-106. DOI: 10.12015/issn.1674-8034.2024.03.017.
[15]
RAMTOHUL T, LEPAGNEY V, BONNEAU C, et al. Use of pretreatment perfusion MRI-based intratumoral heterogeneity to predict pathologic response of triple-negative breast cancer to neoadjuvant chemoimmunotherapy[J/OL]. Radiology, 2024, 312(3): e240575 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/39225608/. DOI: 10.1148/radiol.240575.
[16]
GU J H, TONG T, XU D, et al. Deep learning radiomics of ultrasonography for comprehensively predicting tumor and axillary lymph node status after neoadjuvant chemotherapy in breast cancer patients: a multicenter study[J]. Cancer, 2023, 129(3): 356-366. DOI: 10.1002/cncr.34540.
[17]
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]. Breast Cancer Res, 2024, 26(1): 77. DOI: 10.1186/s13058-024-01836-3.
[18]
LEITHNER D, MAYERHOEFER M E, MARTINEZ D F, et al. Non-invasive assessment of breast cancer molecular subtypes with multiparametric magnetic resonance imaging radiomics[J/OL]. J Clin Med, 2020, 9(6): 1853 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/32545851/. DOI: 10.3390/jcm9061853.
[19]
NIU S X, JIANG W Y, ZHAO N N, et al. Intra- and peritumoral radiomics on assessment of breast cancer molecular subtypes based on mammography and MRI[J]. J Cancer Res Clin Oncol, 2022, 148(1): 97-106. DOI: 10.1007/s00432-021-03822-0.
[20]
NIELSEN T O, LEUNG S C Y, RIMM D L, et al. Assessment of Ki67 in breast cancer: updated recommendations from the international Ki67 in breast cancer working group[J]. J Natl Cancer Inst, 2021, 113(7): 808-819. DOI: 10.1093/jnci/djaa201.
[21]
ALLISON K H, ELIZABETH H HAMMOND M, DOWSETT M, et al. Estrogen and progesterone receptor testing in breast cancer: ASCO/CAP guideline update[J]. J Clin Oncol, 2020, 38(12): 1346-1366. DOI: 10.1200/JCO.19.02309.
[22]
SAUERBREI W, ROYSTON P, BINDER H. Selection of important variables and determination of functional form for continuous predictors in multivariable model building[J]. Stat Med, 2007, 26(30): 5512-5528. DOI: 10.1002/sim.3148.
[23]
CARTER J V, PAN J M, RAI S N, et al. ROC-ing along: Evaluation and interpretation of receiver operating characteristic curves[J]. Surgery, 2016, 159(6): 1638-1645. DOI: 10.1016/j.surg.2015.12.029.
[24]
ZHENG D, HE X J, JING J. Overview of artificial intelligence in breast cancer medical imaging[J/OL]. J Clin Med, 2023, 12(2): 419 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/36675348/. DOI: 10.3390/jcm12020419.
[25]
LI H, ZHU Y T, BURNSIDE E S, et al. Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set[J/OL]. NPJ Breast Cancer, 2016, 2: 16012 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/27853751/ DOI: 10.1038/npjbcancer.2016.12.
[26]
HUANG T, FAN B, QIU Y Y, et al. Application of DCE-MRI radiomics signature analysis in differentiating molecular subtypes of luminal and non-luminal breast cancer[J/OL]. Front Med, 2023, 10: 1140514 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/37181350/. DOI: 10.3389/fmed.2023.1140514.
[27]
FENG S Q, YIN J D. Dynamic contrast-enhanced magnetic resonance imaging radiomics analysis based on intratumoral subregions for predicting luminal and nonluminal breast cancer[J]. Quant Imaging Med Surg, 2023, 13(10): 6735-6749. DOI: 10.21037/qims-22-1073.
[28]
WU J F, GE L F, JIN Y, et al. Development and validation of an ultrasound-based radiomics nomogram for predicting the luminal from non-luminal type in patients with breast carcinoma[J/OL]. Front Oncol, 2022, 12: 993466 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/36530981/. DOI: 10.3389/fonc.2022.993466.
[29]
INAISHI T, SHIBATA M, ICHIKAWA T, et al. Platelet isoform of phosphofructokinase accelerates malignant features in breast cancer[J/OL]. Oncol Rep, 2022, 47(1): 9 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/34751415/. DOI: 10.3892/or.2021.8220.
[30]
ZHOU Y J, HEITMANN J S, CLAR K L, et al. Platelet-expressed immune checkpoint regulator GITRL in breast cancer[J]. Cancer Immunol Immunother, 2021, 70(9): 2483-2496. DOI: 10.1007/s00262-021-02866-y.
[31]
HUSZNO J, KOŁOSZA Z, MROCHEM-KWARCIAK J, et al. Prognostic value of the neutrophil-lymphocyte, platelet-lymphocyte, and monocyte-lymphocyte ratios in male breast cancer patients[J]. Oncology, 2020, 98(7): 487-492. DOI: 10.1159/000505627.
[32]
AGRAWAL A, GANDHE M B, GUPTA D, et al. Preliminary study on serum lactate dehydrogenase (LDH)-prognostic biomarker in carcinoma breast[J/OL]. J Clin Diagn Res, 2016, 10(3): BC06-BC08 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/27134855/. DOI: 10.7860/JCDR/2016/17111.7364.
[33]
MALHOTRA G, GATTANI R G, SHINDE R K, et al. Significance of serum lactate dehydrogenase as a prognostic marker and outcome predictor in patients with breast cancer[J/OL]. Cureus, 2024, 16(3): e55932 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/38601401/. DOI: 10.7759/cureus.55932.
[34]
DENNISON J B, MOLINA J R, MITRA S, et al. Lactate dehydrogenase B: a metabolic marker of response to neoadjuvant chemotherapy in breast cancer[J]. Clin Cancer Res, 2013, 19(13): 3703-3713. DOI: 10.1158/1078-0432.CCR-13-0623.
[35]
XIE W L, HU J, ZHAO Z H, et al. Development of an accurate breast cancer detection classifier based on platelet RNA[J/OL]. Sci Rep, 2024, 14: 30733 [2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/39730431/. DOI: 10.1038/s41598-024-80175-x.
[36]
YAMAMOTO M, SHIBATA M, TANAKA A, et al. Identification of peripheral blood test parameters predicting the response to palbociclib and endocrine therapy for metastatic breast cancer: a retrospective study in a single institution[J]. Surg Today, 2025, 55(2): 188-196. DOI: 10.1007/s00595-024-02893-z.

PREV Correlation study of atherosclerotic plaques in the middle cerebral artery with recurrent stroke assessed by magnetic resonance vascular wall imaging
NEXT A clinical study on the prediction of Ki-67 expression status in breast cancer by quantitative parameters combined with apparent diffusion coefficient of synthetic MRI
  


LINK


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