Share：
Share this content in WeChat
X
[Chinese][PDF]69761
• Experience Exchanges •
The value of texture analysis combined with TIC in the differential diagnosis of breast invasive ductal carcinoma and fibroadenoma
WANG Liang  MEI Haiqing  PENG Hongfeng  ZHANG Dongyou  HAN Rui 

Cite this article as: Wang L, Mei HQ, Peng HF, et al. The value of texture analysis combined with TIC in the differential diagnosis of breast invasive ductal carcinoma and fibroadenoma[J]. Chin J Magn Reson Imaging, 2021, 12(10): 53-56. DOI:10.12015/issn.1674-8034.2021.10.012.


[Abstract] Objective To study the value of texture analysis combined with time-intensity curve (TIC) in the differential diagnosis of breast invasive ductal carcinoma and fibroadenoma. Materials andMethods The MRI images of 75 female patients (48 cases of breast invasive ductal carcinoma and 27 cases of breast fibroadenoma) confirmed by pathology were collected by retrospective method. The TIC were drawn and the five analysis methods of histogram, absolute gradient, run matrix, co-occurrence matrix and autoregressive model in texture analysis software were used to extract texture features of breast lesions on enhanced image, and obtain 306 texture feature parameters; using three statistical methods: Fisher coefficient (Fisher), classification error probability and average correlation coefficients (POE+ACC) and mutual information coefficient (MI), 10 optimal texture parameters were selected to distinguish breast invasive ductal carcinoma and fibroadenoma. The principal component analysis (PCA), linear discriminant analysis (LDA) and non-linear discriminant analysis (NDA) of B11 program were used to reduce the dimension and classify the 10 optimal texture parameters, and the minimum error rate of lesions under the optimal texture parameters was calculated. The sensitivity, specificity and accuracy of TIC method, texture analysis method and the combination of the two methods were analyzed.Results Fisher+NDA or POE+ACC+NDA combination had the lowest misjudgment rate (4%), and the 10 best texture parameters for modeling were: Fisher+NDA were GeoW1, S (5, -5) Entropy, S (5, 5) Correlat, S (4, -4) Entropy, S (5, 0) Entropy, S (5, 5) Entropy, eta2, S (4, 0) Entropy, Teta3, S (3, -3) Entropy;Poe+ACC+NDA were GeoYo, Vertl_Fraction, GeoW5b, GeoW4, S (5, 5) CorrelatTeta1, Vertl_ShrtREmp, GeoNx, GeoAox, GeoX. The sensitivity of TIC, texture analysis and the combination of the two methods were 87.5%, 93.8%, 97.9%; the specificity were 29.6%, 11.1%, 14.8%; the accuracy were 66.7%, 64.0%, 68.0%.Conclusion On the basis of routine MRI examination and enhancement, the sensitivity and accuracy of breast invasive ductal carcinoma and breast fibroadenoma can be improved by using TIC and MRI texture parameter analysis, which has certain value in the differential diagnosis of breast fibroadenoma and invasive ductal carcinoma.
[Keywords] breast tumor；breast fibroadenoma；breast invasive ductal carcinoma；differential diagnosis；magnetic resonance imaging；texture analysis；time-intensity curve

WANG Liang   MEI Haiqing   PENG Hongfeng   ZHANG Dongyou   HAN Rui*  

Department of Radiology, Wuhan No.1 Hospital, Wuhan 430022, China

Han R, E-mail: 1021779149@qq.com

Conflicts of interest   None.

ACKNOWLEDGMENTS Wuhan Medical Research Project General Project-Key Project (WX18B08).
Received  2021-04-12
Accepted  2021-06-28
DOI: 10.12015/issn.1674-8034.2021.10.012
Cite this article as: Wang L, Mei HQ, Peng HF, et al. The value of texture analysis combined with TIC in the differential diagnosis of breast invasive ductal carcinoma and fibroadenoma[J]. Chin J Magn Reson Imaging, 2021, 12(10): 53-56. DOI:10.12015/issn.1674-8034.2021.10.012.

[1]
He JG, Hou JZ, Yan YZ. Analysis on the time trends of female breast cancer death and disease burden in cancer registration areas in China,2005-2013[J]. Chin J Cancer Prev Treat, 2019, 26(8): 523-528. DOI: 10.16073/j.cnki.cjcpt.2019.08.001.
[2]
Sun PF, Liu JJ, Liu PF, et al. Quantitive Analysis of Morphology and Signal Characteristics on MRI of Breast Carcinoma with Medullary Features[J]. J Clin Radiol, 2018, 37(9): 1450-1453. DOI: 10.13437/j.cnki.jcr.2018.09.009.
[3]
Yuan CR, Jin F, Guo XL, et al. Correlation Analysis of Breast Cancer DWI Combined with DCE-MRI Imaging Features with Molecular Subtypes and Prognostic Factors[J]. J Med Syst, 2019, 43(4): 83. DOI: 10.1007/s10916-019-1197-5.
[4]
Li H, Sun H, Liu SQ, et al. Assessing the performance of benign and malignant breast lesion classification with bilateral TIC differentiation and other effective features in DCE‐MRI[J]. J Magn Reson Imaging, 2019, 50: 465–473. DOI: 10.1002/jmri.26646.
[5]
Wang L, Jiang YH. Sensitivity analysis and process optimization of multiple imaging techniques in the diagnosis of breast tumors[J]. J Pract Radiol, 2018, 34(10): 1615-1617. DOI: 10.3969/j.issn.1002-1671.2018.10.034.
[6]
Li LL, Zhu SC, Wu S, et al. Correlation of quantitative parameters from dynamic contrast-enhanced MRI with pathological grades of esophageal squamous cell carcinoma[J]. Chin J Radiol, 2018, 52(3): 204-208. DOI: 10.3760/cma.j.issn.1005-1201.2018.03.009.
[7]
Lee J, Kim SH, Kang BJ. Prognostic Factors of Disease Recurrence in Breast Cancer Using Quantitative and Qualitative Magnetic Resonance Imaging (MRI) Parameters[J]. Sci Rep, 2020, 10(1): 7598. DOI: 10.1038/s41598-020-64564-6.
[8]
Kuroki Y, Ohashi N , Watanabe K, et al. Evaluation of Early Response to Neoadjuvant Chemotherapy or Breast Cancer: Usefulness of Texture Analysis of DCE and Histogram Analysis of DW-MRI [Presidential Award Proceedings][J]. J Magn Reson Imaging, 2019, 39(1): 25-28. DOI: 10.2463/jjmrm.2018-1663.
[9]
Wang YF, Liao X, Xiao F, et al. Magnetic Resonance Imaging Texture Analysis in Differentiating Benign and Malignant Breast Lesions of Breast Imaging Reporting and Data System 4: A Preliminary Study[J]. J Comput Assist Tomogr, 2020, 44(1): 83-89. DOI: 10.1097/RCT.0000000000000969.
[10]
Cao K, Zhao B, Li XT, et al. Texture Analysis of Dynamic Contrast-Enhanced MRI in Evaluating Pathologic Complete Response (pCR) of Mass-Like Breast Cancer after Neoadjuvant Therapy[J]. J Oncol, 2019, 2019: 1-7. DOI: 10.1155/2019/4731532.
[11]
Sannachi L, Gangeh M, Tadayyon H, et al. Breast Cancer Treatment Response Monitoring Using Quantitative Ultrasound and Texture Analysis: Comparative Analysis of Analytical Models-ScienceDirect[J]. Transl Oncol, 2019, 12(10): 1271-1281. DOI: 10.1016/j.tranon.2019.06.004.
[12]
Na LE, Kang D, Son EJ, et al. Texture analysis using machine learning-based 3-T magnetic resonance imaging for predicting recurrence in breast cancer patients treated with neoadjuvant chemotherapy[J]. Eur Radiol, 2021(3): 1-13. DOI: 10.1007/s00330-021-07816-x.
[13]
Loose J, Harz MT, Laue H, et al. Assessment of texture analysis on DCE-MRI data for the differentiation of breast tumor lesions[J]. Biophys J, 2009, 97(12): 3113-22. DOI: 10.1016/j.bpj.2009.09.025.
[14]
Yuan P, Ying JM. Research Progress on molecular characteristics of invasive ductal carcinoma and invasive lobular carcinoma of the breast[J]. Chin J Pathol, 2018, 47(10): 808-811. DOI: 10.3760/cma.j.issn.0529-5807.2018.10.021.
[15]
Jones B, Thomas G, Sprenger J, et al. Peri‐tumoural stroma collagen organization of invasive ductal carcinoma assessed by polarized light microscopy differs between OncotypeDX risk group[J]. J Biophotonics, 2020, 13(11): e202000188. DOI: 10.1002/jbio.202000188.
[16]
Zhao HQ. The prognosis of invasive ductal carcinoma, lobular carcinoma and mixed ductal and lobular carcinoma according to molecular subtypes of the breast[J]. Breast Cancer, 2020, 28(2): 187-195. DOI: 10.1007/s12282-020-01146-4.
[17]
Lei MF, Deng HL, Jin HK, et al. The Value of Ipsilateral Breast Vascularity in Differential Diagnosis of Benign and Malignant Breast Lesions by MRI[J]. Chin J CT MRI, 2020, 18(10): 70-73. DOI: 10.3969/j.issn.1672-5131.2020.10.021.
[18]
Li Y, Song YX, Lang RG, et al. Retrospective study of malignant phyllodes tumors of the breast: younger age, prior fibroadenoma surgery, malignant heterologous elements and surgical margins may predict recurrence[J]. Breast J, 2021, 57(10): 62-70. DOI: 10.1016/j.breast.2021.03.001.
[19]
Erickson LA, Chen B. Fibroadenoma of the Breast[J]. Mayo Clin Proc, 2020, 95(11): 2573-2574. DOI: 10.1016/j.mayocp.2020.08.040.
[20]
Li YC, Zhang L, Liang W, et al. Differential diagnosis of breast medullary carcinoma and fibroadenoma by MRI[J]. Chin J Magn Reson Imag, 2020, 11(2): 124-128. DOI: 10.12015/issn.1674-8034.2020.02.010.
[21]
Wang J, Tang WW, Tian ZF, et al. Correlation between DCE-MRI parameters/ADC and pathological molecular prognostic markers of breast cancer[J]. Chin J Magn Reson Imag, 2021, 12(3): 76-79. DOI: 10.12015/issn.1674-8034.2021.03.017.

PREV Image features of atypical teratoid/rhabdoid tumor of central nervous system in children
NEXT The value of Gd-EOB-DTPA-enhanced MRI nomogram model in predicting microvascular invasion of small solitary hepatocellular carcinoma
  


LINK


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