Share：
Share this content in WeChat
X
[Chinese][PDF]5545
• Clinical Article •
Application value of radiomics based on DCE-MRI combined with DKI in predicting triple-negative breast cancer
GUAN Chuanguo  SHAO Shuo  ZHENG Ning  CHEN Wenjing  ZHAO Xiaomeng  WU Jianwei 

Cite this article as: GUAN C G, SHAO S, ZHENG N, et al. Application value of radiomics based on DCE-MRI combined with DKI in predicting triple-negative breast cancer[J]. Chin J Magn Reson Imaging, 2025, 16(2): 35-43. DOI:10.12015/issn.1674-8034.2025.02.006.


[Abstract] Objective To construct a radiomics model based on dynamic contrast-enhanced MRI (DCE-MRI) and diffusion kurtosis imaging (DKI), and evaluate its diagnostic value for triple-negative breast cancer (TNBC).Materials and Methods A retrospective analysis was performed on the clinical data of 165 breast cancer patients, who were divided into a non-TNBC group (120 cases) and a TNBC group (45 cases) based on pathological results. All patients underwent preoperative DCE-MRI and DKI scans. The patients were randomly split into a training set (n = 132) and a test set (n = 33) at a ratio of 8∶2. A three-dimensional (3D) region of interest (ROI) was delineated in the lesion area from the phase Ⅱ DCE-MRI images, the mean kurtosis (MK) map, and the mean diffusivity (MD) map, and radiomics features were extracted. Feature reduction and selection were performed using K-best, maximum relevance and minimum redundancy (mRMR), and least absolute shrinkage and selection operator (LASSO) algorithms. Logistic regression (LR) classifiers were used to build the phase Ⅱ DCE model, DKI parameter map models (MD, MK, MD+MK), and the combined model (DCE-MRI+MD+MK). The stability of the models was validated using five-fold cross-validation. The models' predictive performance was evaluated by receiver operating characteristic (ROC) curve and area under the curve (AUC), and statistical differences between models were analyzed using the DeLong test. Finally, decision curve analysis (DCA) was performed to assess the clinical utility of the radiomics models.Results A total of 2286 radiomics features were extracted from the 3D ROIs of each sequence. From the Phase Ⅱ DCE-MRI, MD+MK, MD, MK, and DCE-MRI+MD+MK sequences, 8, 9, 12, 7, and 21 features were selected, respectively, that were associated with TNBC. The AUCs of the Phase Ⅱ DCE-MRI model, MD+MK model, MD model, and MK model in the test set were 0.810, 0.769, 0.676, and 0.625, respectively. The combined model (DCE-MRI+MD+MK) achieved an AUC of 0.884 in the test set, with an accuracy, sensitivity, and specificity of 78.8%, 79.2%, and 77.8%, respectively. Finally, a nomogram model was developed by integrating clinical features with radiomics features. The results indicated that the radiomics combined model (DCE-MRI+MD+MK) outperformed the MD+MK model, MD model, MK models, and Phase Ⅱ DCE-MRI model, but there was no statistically significant difference in AUC and DCA between the combined model and the nomogram model (P > 0.05), suggesting that the radiomics combined model (DCE-MRI+MD+MK) can provide diagnostic performance similar to that of the nomogram model in clinical practice.Conclusions The radiomics combined model (DCE-MRI+MD+MK) based on DCE-MRI and DKI parameter maps, as well as the nomogram model, can effectively predict TNBC preoperatively, helping clinicians in diagnosing TNBC, formulating treatment plans, and improving prognosis.
[Keywords] breast cancer；radiomics；dynamic contrast-enhanced；diffusion kurtosis imaging；magnetic resonance imaging；diagnostic value

GUAN Chuanguo1   SHAO Shuo2   ZHENG Ning2*   CHEN Wenjing3   ZHAO Xiaomeng1   WU Jianwei1  

1 Clinical Medical College, Jining Medical University, Jining 272013, China

2 Magnetic Resonance Imaging Room, Jining First People's Hospital, Jining 272000, China

3 United Imaging Intelligence Medical Technology Co., Ltd., Beijing 100089, China

Corresponding author: ZHENG N, E-mail: zhengning_369@163.com

Conflicts of interest   None.

Received  2024-09-23
Accepted  2025-02-10
DOI: 10.12015/issn.1674-8034.2025.02.006
Cite this article as: GUAN C G, SHAO S, ZHENG N, et al. Application value of radiomics based on DCE-MRI combined with DKI in predicting triple-negative breast cancer[J]. Chin J Magn Reson Imaging, 2025, 16(2): 35-43. DOI:10.12015/issn.1674-8034.2025.02.006.

[1]
SUNG H, FERLAY J, SIEGEL R L, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2021, 71(3): 209-249. DOI: 10.3322/caac.21660.
[2]
Global cancer burden growing, amidst mounting need for services[J]. Saudi Med J, 2024, 45(3): 326-327. DOI: 10.3322/caac.21660.
[3]
SIEGEL R L, MILLER K D, JEMAL A. Cancer statistics, 2020[J]. CA Cancer J Clin, 2020, 70(1): 7-30. DOI: 10.3322/caac.21590.
[4]
CHOI Y, KIM S H, YOUN I K, et al. Rim sign and histogram analysis of apparent diffusion coefficient values on diffusion-weighted MRI in triple-negative breast cancer: Comparison with ER-positive subtype[J/OL]. PLoS One, 2017, 12(5): e0177903 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/28542297/. DOI: 10.1371/journal.pone.0177903.
[5]
DENT R, TRUDEAU M, PRITCHARD K I, et al. Triple-negative breast cancer: clinical features and patterns of recurrence[J]. Clin Cancer Res, 2007, 13(15Pt 1): 4429-4434. DOI: 10.1158/1078-0432.CCR-06-3045.
[6]
YIN L, DUAN J J, BIAN X W, et al. Triple-negative breast cancer molecular subtyping and treatment progress[J/OL]. Breast Cancer Res, 2020, 22(1): 61 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/32517735/. DOI: 10.1186/s13058-020-01296-5.
[7]
TONG L, YU X L, WANG S, et al. Research progress on molecular subtyping and modern treatment of triple-negative breast cancer[J/OL]. Breast Cancer, 2023, 15: 647-658 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/37644916/. DOI: 10.2147/BCTT.S426121.
[8]
JOCHELSON M. Advanced imaging techniques for the detection of breast cancer[J/OL]. Am Soc Clin Oncol Educ Book, 2012: 65-69 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/24451711/. DOI: 10.14694/EdBook_AM.2012.32.223.
[9]
ZHONG Y Z, GUAN J T, MA Y F, et al. Role of imaging modalities and N-acetylcysteine treatment in sepsis-associated encephalopathy[J]. ACS Chem Neurosci, 2023, 14(11): 2172-2182. DOI: 10.1021/acschemneuro.3c00180.
[10]
TEH I, MCCLYMONT D, CARRUTH E, et al. Improved compressed sensing and super-resolution of cardiac diffusion MRI with structure-guided total variation[J]. Magn Reson Med, 2020, 84(4): 1868-1880. DOI: 10.1002/mrm.28245.
[11]
QI X, WANG W L, PAN S Y, et al. Predictive value of triple negative breast cancer based on DCE-MRI multi-phase full-volume ROI clinical radiomics model[J]. Acta Radiol, 2024, 65(2): 173-184. DOI: 10.1177/02841851231215145.
[12]
PANTHI B, MOHAMED R M, ADRADA B E, et al. Longitudinal dynamic contrast-enhanced MRI radiomic models for early prediction of response to neoadjuvant systemic therapy in triple-negative breast cancer[J/OL]. Front Oncol, 2023, 13: 1264259 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/37941561/. DOI: 10.3389/fonc.2023.1264259.
[13]
MA M M, GAN L Y, JIANG Y, et al. Radiomics analysis based on automatic image segmentation of DCE-MRI for predicting triple-negative and nontriple-negative breast cancer[J/OL]. Comput Math Methods Med, 2021, 2021: 2140465 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/34422088/. DOI: 10.1155/2021/2140465.
[14]
KANG H S, KIM J Y, KIM J J, et al. Diffusion kurtosis MR imaging of invasive breast cancer: correlations with prognostic factors and molecular subtypes[J]. J Magn Reson Imaging, 2022, 56(1): 110-120. DOI: 10.1002/jmri.27999.
[15]
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.
[16]
WANG W W, LV S Q, XUN J, et al. Comparison of diffusion kurtosis imaging and dynamic contrast enhanced MRI in prediction of prognostic factors and molecular subtypes in patients with breast cancer[J/OL]. Eur J Radiol, 2022, 154: 110392 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/35679701/. DOI: 10.1016/j.ejrad.2022.110392.
[17]
XU A Q, CHU X F, ZHANG S J, et al. Prediction breast molecular typing of invasive ductal carcinoma based on dynamic contrast enhancement magnetic resonance imaging radiomics characteristics: a feasibility study[J/OL]. Front Oncol, 2022, 12: 799232 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/35664741/. DOI: https://pubmed.ncbi.nlm.nih.gov/35664741/10.3389/fonc.2022.799232.
[18]
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 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/37181350/. DOI: 10.3389/fmed.2023.1140514.
[19]
HUANG G L, DU S Y, GAO S, et al. Molecular subtypes of breast cancer identified by dynamically enhanced MRI radiomics: the delayed phase cannot be ignored[J/OL]. Insights Imaging, 2024, 15(1): 127 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/38816553/. DOI: 10.1186/s13244-024-01713-9.
[20]
SHENG W Y, XIA S L, WANG Y R, et al. Invasive ductal breast cancer molecular subtype prediction by MRI radiomic and clinical features based on machine learning[J/OL]. Front Oncol, 2022, 12: 964605 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/36172153/. DOI: 10.3389/fonc.2022.964605.
[21]
LIN Q, CHEN A H, ZHANG T T. Diagnostic value of DCE-MRI texture analysis for molecular typing of breast cancer[J]. Chin J Magn Reson Imag, 2023, 14(12): 40-48. DOI: 10.12015/issn.1674-8034.2023.12.007.
[22]
WU R, LI X Y, CHEN S, et al. Diagnostic value of intratumoral and peritumoral radiomics model based on DCE-MRI in predicting the triple-negative breast cancer[J]. J Med Res Combat Trauma Care, 2023, 36(4): 375-381. DOI: 10.16571/j.cnki.2097-2768.2023.04.007.
[23]
LI S P, PADHANI A R, JANE TAYLOR N, et al. Vascular characterisation of triple negative breast carcinomas using dynamic MRI[J]. Eur Radiol, 2011, 21(7): 1364-1373. DOI: 10.1007/s00330-011-2061-2.
[24]
YOUK J H, SON E J, CHUNG J, et al. Triple-negative invasive breast cancer on dynamic contrast-enhanced and diffusion-weighted MR imaging: comparison with other breast cancer subtypes[J]. Eur Radiol, 2012, 22(8): 1724-1734. DOI: 10.1007/s00330-012-2425-2.
[25]
ZHANG D D, GENG X C, SUO S T, et al. The predictive value of DKI in breast cancer: Does tumour subtype affect pathological response evaluations?[J/OL]. Magn Reson Imaging, 2022, 85: 28-34 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/34662700/. DOI: 10.1016/j.mri.2021.10.013.
[26]
JENSEN J H, HELPERN J A, RAMANI A, et al. Diffusional kurtosis imaging: the quantification of non-Gaussian water diffusion by means of magnetic resonance imaging[J]. Magn Reson Med, 2005, 53(6): 1432-1440. DOI: 10.1002/mrm.20508.
[27]
ZHOU W P, ZAN X Y, HU X Y, et al. Characterization of breast lesions using diffusion kurtosis model-based imaging: an initial experience[J]. J Xray Sci Technol, 2020, 28(1): 157-169. DOI: 10.3233/XST-190590.
[28]
WANG W W, ZHANG X D, ZHU L M, et al. Prediction of prognostic factors and genotypes in patients with breast cancer using multiple mathematical models of MR diffusion imaging[J/OL]. Front Oncol, 2022, 12: 825264 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/35174093/. DOI: 10.3389/fonc.2022.825264.
[29]
CHEN K W, YU C X, PAN J L, et al. Prediction of the Nottingham prognostic index and molecular subtypes of breast cancer through multimodal magnetic resonance imaging[J/OL]. Magn Reson Imaging, 2024, 108: 168-175 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/38408689/. DOI: 10.1016/j.mri.2024.02.012.
[30]
LIU S H, SHAO S, WEI K J, et al. Diagnostic value of DCE-MRI combined with DKI in predicting the triple negative breast cancer[J]. Chin J Magn Reson Imag, 2023, 14(5): 110-115. DOI: 10.12015/issn.1674-8034.2023.05.020.
[31]
SHI Z T, HE X Q, SHAO K, et al. Prediction of the expression of molecular subtypes in breast cancer based on diffusion kurtosis imaging and dynamic contrast enhancement imaging[J]. J Clin Radiol, 2023, 42(7): 1087-1092. DOI: 10.13437/j.cnki.jcr.2023.07.031.
[32]
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 [2024-09-23]. https://pubmed.ncbi.nlm.nih.gov/32545851/. DOI: 10.3390/jcm9061853.
[33]
ZHAO X M, SHAO S, ZHENG N, et al. Application value of IVIM, DKI and DCE-MRI radiomics predicting HER-2 expression in breast cancer[J]. Chin J Magn Reson Imag, 2024, 15(7): 105-111. DOI: 10.12015/issn.1674-8034.2024.07.018.

PREV Comparative study of myocardial mechanical function changes before and after coronary artery bypass grafting using cardiac magnetic resonance feature tracking technique
NEXT The value of Gd-EOB-DTPA-enhanced MRI radiomics in predicting Glypican-3 positive expression in hepatocellular carcinoma
  


LINK


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