Share：
Share this content in WeChat
X
[Chinese][PDF]3931
• Clinical Article •
Value of MRI image omics model in preoperative prediction of human epidermal growth factor receptor 2 expression in breast cancer
LI Zhouli  CHEN Jiming  GAO Jing  WU Lili  DING Jun  ZHANG Aijuan  SHAO Ying 

Cite this article as: LI Z L, CHEN J M, GAO J, et al. Value of MRI image omics model in preoperative prediction of human epidermal growth factor receptor 2 expression in breast cancer[J]. Chin J Magn Reson Imaging, 2023, 14(4): 82-88. DOI:10.12015/issn.1674-8034.2023.04.014.


[Abstract] Objective To explore the value of conventional and functional MRI radiomics in prediction of human epidermal growth factor receptor 2 (HER-2) status in breast cancel.Materials and Methods In this retrospective study, a total of 100 patients with breast cancer confirmed by surgery and pathology were enrolled from January 2016 to May 2020 in our hospital, including 57 cases of HER-2 positive and 85 cases of HER-2 negative. The patients were randomly divided into training group [100 cases, HER-2(+) 60 cases, HER-2(-) 40 cases], testing group [42 cases, HER-2(+) 25 cases, HER-2(-) 17 cases]. All patients underwent routine and dynamic contrast enhanced magnetic resonance imaging scans of the breast. A region of interest (ROI) of the primary breast tumor in each patient was delineated, and then the texture features of the ROI were extracted by AK. The minimum redundancy maximum redundancy and the least absolute shrinkage and selection operator methods were used to reduce the dimensionality of texture features and establish radiomics signature. Multivariate logistic regression was used to establish individualized prediction model (including clinical factors and radiomics signature). The performance of the model was assessed by area under the receiver operating characteristic curve (AUC). Decision curve analysis (DCA) were used to evaluate the clinical usefulness.Results The area under the curve (AUC) of the clinical prediction model for positive HER-2 in the training group and the testing group was 0.81 and 0.69, respectively. The AUC of the combined sequentomics label was 0.89 and 0.81, respectively. The AUC of personalized prediction models was 0.94 and 0.87, respectively. DCA indicated that the value of individualized prediction model was higher than clinical prediction model and joint radiomics signature in clinical practice.Conclusions The individualized prediction model is superior to clinical prediction model and joint radiomics signature, and it has high value in predicting of HER-2 status.
[Keywords] breast cancer；human epidermal growth factor；radiomics；prediction model；prognosis；magnetic resonance imaging

LI Zhouli   CHEN Jiming*   GAO Jing   WU Lili   DING Jun   ZHANG Aijuan   SHAO Ying  

Department of Radiology, Yijishan Hospital of Wannan Medical College, Wuhu 241001, China

Corresponding author: Chen JM, E-mail: yjsyycjm@126.com

Conflicts of interest   None.

Received  2022-09-16
Accepted  2023-04-11
DOI: 10.12015/issn.1674-8034.2023.04.014
Cite this article as: LI Z L, CHEN J M, GAO J, et al. Value of MRI image omics model in preoperative prediction of human epidermal growth factor receptor 2 expression in breast cancer[J]. Chin J Magn Reson Imaging, 2023, 14(4): 82-88. DOI:10.12015/issn.1674-8034.2023.04.014.

[1]
HE J, CHEN W Q, LI N, et al. China guideline for the screening and early detection of female breast cancer (2021, Beijing)[J]. China Cancer, 2021, 30(3): 161-191. DOI: 10.11735/j.issn.1004-0242.2021.03.A001.
[2]
HAN L H, LI L, WANG N, et al. Relationship of epidermal growth factor receptor expression with clinical symptoms and metastasis of invasive breast cancer[J]. J Interferon Cytokine Res, 2018, 38(12): 578-582. DOI: 10.1089/jir.2018.0085.
[3]
ZHAO Y, YANG N, WANG X, et al. Potential roles of lymphovascular space invasion based on tumor characteristics provide important prognostic information in T1 tumors with ER and HER2 positive breast cancer[J]. Clin Transl Oncol, 2020, 22(12): 2275-2285. DOI: 10.1007/s12094-020-02369-9.
[4]
WU J, SUN X L, WANG J, et al. Identifying relations between imaging phenotypes and molecular subtypes of breast cancer: model discovery and external validation[J]. J Magn Reson Imaging, 2017, 46(4): 1017-1027. DOI: 10.1002/jmri.25661.
[5]
SUTTON E J, OH J H, DASHEVSKY B Z, et al. Breast cancer subtype intertumor heterogeneity: MRI-based features predict results of a genomic assay[J]. J Magn Reson Imaging, 2015, 42(5): 1398-1406. DOI: 10.1002/jmri.24890.
[6]
WUERSTLEIN R, HARBECK N. Neoadjuvant therapy for HER2-positive breast cancer[J]. Rev Recent Clin Trials, 2017, 12(2): 81-92. DOI: 10.2174/1574887112666170202165049.
[7]
KANGLEON-TAN H L, SIM J, YOU J Y, et al. Omission of chemotherapy for hormone receptor-positive and human epidermal growth factor receptor 2-negative breast cancer: patterns of treatment and outcomes from the Korean Breast Cancer Society Registry[J]. Ann Surg Treat Res, 2022, 103(6): 313-322. DOI: 10.4174/astr.2022.103.6.313.
[8]
HAN L, ZHU Y B, LIU Z Y, et al. Radiomic nomogram for prediction of axillary lymph node metastasis in breast cancer[J]. Eur Radiol, 2019, 29(7): 3820-3829. DOI: 10.1007/s00330-018-5981-2.
[9]
KÖSEOĞLU R D, MARKOÇ F, MÜSLEHIDDINOĞLU A, et al. HER-2/neu and hormone receptor analysis in breast carcinomas and their association with clinicopathologic parameters[J]. Eur J Breast Health, 2019, 15(1): 43-50. DOI: 10.5152/ejbh.2018.4118.
[10]
LI C L, SONG L R, YIN J D. Intratumoral and peritumoral radiomics based on functional parametric maps from breast DCE-MRI for prediction of HER-2 and ki-67 status[J]. J Magn Reson Imaging, 2021, 54(3): 703-714. DOI: 10.1002/jmri.27651.
[11]
FAN Y, PAN X L, YANG F, et al. Preoperative computed tomography radiomics analysis for predicting receptors status and ki-67 levels in breast cancer[J]. Am J Clin Oncol, 2022, 45(12): 526-533. DOI: 10.1097/COC.0000000000000951.
[12]
ZHU W S, SHI S Y, YANG Z H, et al. Radiomics model based on preoperative gadoxetic acid-enhanced MRI for predicting liver failure[J]. World J Gastroenterol, 2020, 26(11): 1208-1220. DOI: 10.3748/wjg.v26.i11.1208.
[13]
CONTI A, DUGGENTO A, INDOVINA I, et al. Radiomics in breast cancer classification and prediction[J]. Semin Cancer Biol, 2021, 72: 238-250. DOI: 10.1016/j.semcancer.2020.04.002.
[14]
WANG Z Y, MAO N, XIE H Z. Research progress of MRI imaging of breast cancer[J]. Chin J Magn Reson Imaging, 2021, 12(1): 109-111. DOI: 10.12015/issn.1674-8034.2021.01.026.
[15]
GRANZIER R W Y, VERBAKEL N M H, IBRAHIM A, et al. MRI-based radiomics in breast cancer: feature robustness with respect to inter-observer segmentation variability[J/OL]. Sci Rep, 2020, 10(1): 14163 [2022-09-15]. https://pubmed.ncbi.nlm.nih.gov/32843663/. DOI: 10.1038/s41598-020-70940-z.
[16]
VALDORA F, HOUSSAMI N, ROSSI F, et al. Rapid review: radiomics and breast cancer[J]. Breast Cancer Res Treat, 2018, 169(2): 217-229. DOI: 10.1007/s10549-018-4675-4.
[17]
HA R, MUTASA S, KARCICH J, et al. Predicting breast cancer molecular subtype with MRI dataset utilizing convolutional neural network algorithm[J]. J Digit Imaging, 2019, 32(2): 276-282. DOI: 10.1007/s10278-019-00179-2.
[18]
CHENG X, YU R S, XU M, et al. The correlation between functional magnetic resonance imaging features and expression of Her-2 in breast cancer[J]. Natl Med J China, 2019, 99(31): 2440-2444. DOI: 10.3760/cma.j.issn.0376-2491.2019.31.007.
[19]
PARK S H, CHOI H Y, HAHN S Y. Correlations between apparent diffusion coefficient values of invasive ductal carcinoma and pathologic factors on diffusion-weighted MRI at 3.0 Tesla[J]. J Magn Reson Imaging, 2015, 41(1): 175-182. DOI: 10.1002/jmri.24519.
[20]
YANG Y J, SUN Y H. Relationship between HER2 expression and clinicopathological characteristics in breast cancer[J]. J Nanchang Univ Med Sci, 2018, 58(1): 55-59, 64. DOI: 10.13764/j.cnki.ncdm.2018.01.013.
[21]
BITENCOURT A G V, GIBBS P, ROSSI SACCARELLI C, et al. MRI-based machine learning radiomics can predict HER2 expression level and pathologic response after neoadjuvant therapy in HER2 overexpressing breast cancer[J]. EBioMedicine, 2020, 61: 103042. DOI: 10.1016/j.ebiom.2020.103042.
[22]
ZHOU J, TAN H N, LI W, et al. Radiomics signatures based on multiparametric MRI for the preoperative prediction of the HER2 status of patients with breast cancer[J]. Acad Radiol, 2021, 28(10): 1352-1360. DOI: 10.1016/j.acra.2020.05.040.
[23]
SONG B, WANG L, ZHANG Y, et al. Combined detection of HER2, Ki67, and GSTP1 genes on the diagnosis and prognosis of breast cancer[J]. Cancer Biother Radiopharm, 2019, 34(2): 85-90. DOI: 10.1089/cbr.2018.2570.
[24]
CAIN E H, SAHA A, HAROWICZ M R, et al. Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set[J]. Breast Cancer Res Treat, 2019, 173(2): 455-463. DOI: 10.1007/s10549-018-4990-9.
[25]
LEITHNER D, BERNARD-DAVILA B, MARTINEZ D F, et al. Radiomic signatures derived from diffusion-weighted imaging for the assessment of breast cancer receptor status and molecular subtypes[J]. Mol Imaging Biol, 2020, 22(2): 453-461. DOI: 10.1007/s11307-019-01383-w.
[26]
KIM J J, KIM J Y, SUH H B, et al. Characterization of breast cancer subtypes based on quantitative assessment of intratumoral heterogeneity using dynamic contrast-enhanced and diffusion-weighted magnetic resonance imaging[J]. Eur Radiol, 2022, 32(2): 822-833. DOI: 10.1007/s00330-021-08166-4.
[27]
YAMAGUCHI K, NAKAZONO T, EGASHIRA R, et al. Maximum slope of ultrafast dynamic contrast-enhanced MRI of the breast: comparisons with prognostic factors of breast cancer[J]. Jpn J Radiol, 2021, 39(3): 246-253. DOI: 10.1007/s11604-020-01049-6.
[28]
SATAKE H, ISHIGAKI S, ITO R, et al. Radiomics in breast MRI: current progress toward clinical application in the era of artificial intelligence[J]. Radiol Med, 2022, 127(1): 39-56. DOI: 10.1007/s11547-021-01423-y.
[29]
XUE K, LI Z L, LI Z H, et al. Identify HER-2 over expression breast cancer based on radiomics of multi-parametric MRI[J]. Radiol Pract, 2020, 35(2): 186-189. DOI: 10.13609/j.cnki.1000-0313.2020.02.012.
[30]
LIANG C S, CUI Y N, YANG W C, et al. T2WI-based radiomics signatures for predicting human epidermal growth factor receptor 2 status in breast cancer[J]. Chin J Med Imaging Technol, 2019, 35(4): 555-559. DOI: 10.13929/j.1003-3289.201808188.
[31]
JIANG Z, SONG L, LU H, et al. The potential use of DCE-MRI texture analysis to predict HER2 2+ status[J/OL]. Front Oncol, 2019, 9: 242 [2022-09-15]. https://pubmed.ncbi.nlm.nih.gov/31032222/. DOI: 10.3389/fonc.2019.00242.
[32]
LU H, YIN J. Texture analysis of breast DCE-MRI based on intratumoral subregions for predicting HER2 2+ status[J/OL]. Front Oncol, 2020, 10: 543 [2022-09-15]. https://pubmed.ncbi.nlm.nih.gov/32373531/. DOI: 10.3389/fonc.2020.00543.

PREV Value of edema on T2WI before treatment in predicting the efficacy of neoadjuvant chemotherapy for breast cancer
NEXT Quantitative assessment of liver and pancreatic fat infiltration and its correlation with insulin resistance in type 2 diabetic patients by 3D-IDEAL-IQ
  


LINK


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