Share：
Share this content in WeChat
X
[Chinese][PDF]7452
• Clinical Article •
An integrated model based on feature fusion for classifying molecular subtypes of breast cancer
ZHANG Lei  YANG Lifeng  JIAO Xiong 

Cite this article as: ZHANG L, YANG L F, JIAO X. An integrated model based on feature fusion for classifying molecular subtypes of breast cancer[J]. Chin J Magn Reson Imaging, 2023, 14(3): 58-64. DOI:10.12015/issn.1674-8034.2023.03.011.


[Abstract] Objective To construct an integrated support vector machine (SVM) model for classifying molecular subtypes of breast cancer by fusing traditional radiomics features and convolutional neural network features, and the value of this model for classifying molecular subtypes of breast cancer was explored.Materials and Methods One hundred and eighty-nine patients with pathologically confirmed breast cancer in the Duke-Breast-Cancer-MRI dataset were retrospectively analyzed, including 71 cases of Luminal type, 57 cases of human epidermal growth factor receptor 2 (HER-2) overexpression type, and 61 cases of triple-negative type. After preprocessing the dynamic contrast-enhanced MRI (DCE-MRI) images of all patients, the cases were divided into a training set (n=151) and testing set (n=38) in the ratio of 8∶2. The features were extracted from the region of interest (ROI) of the patient's lesion using traditional radiomics model and the DenseNet169 network model, then the traditional radiomics features were further filtered using Spearman correlation coefficient and the least absolute shrinkage and selection operator (LASSO) algorithm. Finally, the SVM-integrated classification model was constructed using the fused feature set. The macro-averaging method was used to plot the diagnostic effect of the integrated model using the receiver operating characteristic (ROC) curve.Results The traditional imaging histology features of three molecular subtypes of breast cancer were filtered to obtain 51, 49, and 20 feature labels, which were fused and modeled with 1664 features extracted by convolutional neural networks, respectively. The area under the curve (AUC) value of the classifier constructed by Luminal and HER-2 overexpression type was 0.880 [95% confidence interval (CI):0.814-0.946], the AUC value of the classifier constructed by Luminal and triple-negative type was 0.861 (95% CI: 0.791-0.931), and the AUC value of the classifier constructed by HER-2 overexpression type and triple-negative type was 0.696 (95% CI: 0.571-0.822). The AUC value of the SVM integrated model consisting of three binary classifiers was 0.820 (95% CI: 0.725-0.915).Conclusions The integrated SVM model based on feature fusion showed good results in classifying three molecular subtypes of breast cancer, which is an important guide for the preoperative classification of molecular subtypes of breast cancer.
[Keywords] breast cancer；molecular subtypes；feature fusion；support vector machine；magnetic resonance imaging

ZHANG Lei1   YANG Lifeng2   JIAO Xiong1*  

1 College of Biomedical Engineering, Taiyuan University of Technology, Jinzhong 030600, China

2 College of Information and Computer, Taiyuan University of Technology, Jinzhong 030600, China

Corresponding author: Jiao X, E-mail: jiaoxiong@tyut.edu.cn

Conflicts of interest   None.

ACKNOWLEDGMENTS Natural Science Foundation of Shanxi Province (No. 201801D121232).
Received  2022-10-26
Accepted  2023-03-07
DOI: 10.12015/issn.1674-8034.2023.03.011
Cite this article as: ZHANG L, YANG L F, JIAO X. An integrated model based on feature fusion for classifying molecular subtypes of breast cancer[J]. Chin J Magn Reson Imaging, 2023, 14(3): 58-64. DOI:10.12015/issn.1674-8034.2023.03.011.

[1]
GIAQUINTO A N, SUNG H, MILLER K D, et al. Breast cancer statistics, 2022[J]. CA Cancer J Clin, 2022, 72(6): 524-541. DOI: 10.3322/caac.21754.
[2]
SIEGEL R L, MILLER K D, JEMAL A. Cancer statistics, 2015[J]. CA A Cancer J Clin, 2015, 65(1): 5-29. DOI: 10.3322/caac.21254.
[3]
SHAO Z M, WU J, JIANG Z F, et al. Expert consensus on neoadjuvant treatment of breast cancer in China(2021 edition)[J]. China Oncol, 2022, 32(1): 80-89. DOI: 10.19401/j.cnki.1007-3639.2022.01.011.
[4]
GOLDHIRSCH A, WINER E P, COATES A S, et al. Personalizing the treatment of women with early breast cancer: highlights of the St Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2013[J]. Ann Oncol, 2013, 24(9): 2206-2223. DOI: 10.1093/annonc/mdt303.
[5]
ZHONG S Y, LEI Y, YU J, et al. Research progress of magnetic resonance imaging in molecular typing of breast cancer[J]. Chin J CT MRI, 2022, 20(3): 186-188. DOI: 10.3969/j.issn.1672-5131.2022.03.062.
[6]
QIN S Z, HUANG X H, WANG F, et al. Value of T2WI-FS radiomics combined with imaging features in predicting the efficacy of HIFU ablation of hysteromyoma[J]. Chin J Magn Reson Imaging, 2022, 13(5): 59-63, 69. DOI: 10.12015/issn.1674-8034.2022.05.011.
[7]
XU R, WANG Z, ZONG T. Edge enhancement of medical image based on improved Gaussian filter[J]. Inf Technol, 2020, 44(4): 75-78. DOI: 10.13274/j.cnki.hdzj.2020.04.016.
[8]
LIU L, LAO S Y, FIEGUTH P W, et al. Median robust extended local binary pattern for texture classification[J]. IEEE Trans Image Process, 2016, 25(3): 1368-1381. DOI: 10.1109/TIP.2016.2522378.
[9]
CHAUHAN V K, DAHIYA K, SHARMA A. Problem formulations and solvers in linear SVM: a review[J].Artif Intell Rev, 2019, 52(2): 803-855. DOI: 10.1007/s10462-018-9614-6.
[10]
RIGATTI S J. Random forest[J]. J Insur Med, 2017, 47(1): 31-39. DOI: 10.17849/insm-47-01-31-39.1.
[11]
ZHANG S, GONG Y H, WANG J J. The development of deep convolution neural network and its applications on computer vision[J]. Chin J Comput, 2019, 42(3): 453-482. DOI: 10.11897/SP.J.1016.2019.00453.
[12]
WANG J X, LEI Z C. A convolutional neural network based on feature fusion for face recognition[J]. Laser & Optoelectron Prog, 2020, 57(10): 339-345. DOI: 10.3788/LOP57.101508.
[13]
ARAÚJO T, ARESTA G, CASTRO E, et al. Classification of breast cancer histology images using Convolutional Neural Networks[J/OL]. PLoS One, 2017, 12(6): e0177544 [2022-10-25]. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0177544. DOI: 10.1371/journal.pone.0177544.
[14]
SUN F Q, CONG C L, ZHANG K, et al. Benign and malignant diagnosis of breast cancer histopathological image based on multi-model neural network[J]. J Chin Comput Syst, 2020, 41(4): 732-735. DOI: 10.3969/j.issn.1000-1220.2020.04.010.
[15]
SAHA A, HAROWICZ M R, GRIMM L J, et al. A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features[J]. Br J Cancer, 2018, 119(4): 508-516. DOI: 10.1038/s41416-018-0185-8.
[16]
SAHA A, HAROWICZ M R, GRIMM L J, et al. Dynamic contrast-enhanced magnetic resonance images of breast cancer patients with tumor locations[DS/OL]. Cancer Imag Archiv, 2021 [2022-10-25]. https://wiki.cancerimagingarchive.net/x/15MvB. DOI: 10.7937/TCIA.e3sv-re93.
[17]
CLARK K, VENDT B, SMITH K, et al. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository[J]. J Digit Imaging, 2013, 26(6): 1045-1057. DOI: 10.1007/s10278-013-9622-7.
[18]
KOO K M, CHA E Y. Image recognition performance enhancements using image normalization[J].Hum Centric Comput Inf Sci, 2017, 7(1): 1-11. DOI: 10.1186/s13673-017-0114-5.
[19]
KUMARI R, GUPTA N, KUMAR N. Image segmentation using improved genetic algorithm[J]. Int J Eng Adv Technol, 2020, 9(1): 1784-1792. DOI: 10.35940/ijeat.F9063.109119.
[20]
VAN GRIETHUYSEN J J M, FEDOROV A, PARMAR C, et al. Computational radiomics system to decode the radiographic phenotype[J/OL]. Cancer Res, 2017, 77(21): e104-e107 [2022-10-25]. https://pubmed.ncbi.nlm.nih.gov/29092951/. DOI: 10.1158/0008-5472.CAN-17-0339.
[21]
WANG Y N, HU C Y, KWOK T, et al. DEMoS: a deep learning-based ensemble approach for predicting the molecular subtypes of gastric adenocarcinomas from histopathological images[J]. Bioinformatics, 2022, 38(17): 4206-4213. DOI: 10.1093/bioinformatics/btac456.
[22]
LIU J W, ZHAO H D, LUO X L, et al. Research progress on batch normalization of deep learning and its related algorithms[J]. Acta Autom Sin, 2020, 46(6): 1090-1120. DOI: 10.16383/j.aas.c180564.
[23]
FAWCETT T. An introduction to ROC analysis[J]. Pattern Recognit Lett, 2006, 27(8): 861-874. DOI: 10.1016/j.patrec.2005.10.010.
[24]
RIBEIRO B, SILVA C. RVM ensemble for text classification[J]. Int J Comput Intell Res, 2007, 3(1): 31-35. DOI: 10.5019/j.ijcir.2007.81.
[25]
KANG S, CHO S, KANG P. Constructing a multi-class classifier using one-against-one approach with different binary classifiers[J]. Neurocomputing, 2015, 149: 677-682. DOI: 10.1016/j.neucom.2014.08.006.
[26]
WANG R, LI W, LI R, et al. Automatic blur type classification via ensemble SVM[J]. Signal Process Image Commun, 2019, 71: 24-35. DOI: 10.1016/j.image.2018.08.003.
[27]
CHO N. Imaging features of breast cancer molecular subtypes: state of the art[J]. J Pathol Transl Med, 2021, 55(1): 16-25. DOI: 10.4132/jptm.2020.09.03.
[28]
CHEN Y S, SUN S J, YU X J, et al. 3.0 T MRI features of breast cancer in different molecular types[J]. Chin J Magn Reson Imaging, 2021, 12(2): 24-28. DOI: 10.12015/issn.1674-8034.2021.02.006.
[29]
WANG S J, FAN M, ZHANG J, et al. Association between DCE-MRI features and molecular subtypes in breast cancer[J]. Chin J Biomed Eng, 2016, 35(5): 533-540. DOI: 10.3969/j.issn.0258-8021.2016.05.004.
[30]
LI W, PING X J, LIU Y H, et al. Value of MRI imaging features in predicting molecular typing of breast cancer[J]. J Clin Radiol, 2021, 40(9): 1709-1714. DOI: 10.13437/j.cnki.jcr.2021.09.012.
[31]
WANG H J, WANG W W, LÜ S Q, et al. Value of multi-parameter diffusion weighted imaging in the differential diagnosis of benign and malignant TIC type Ⅱ breast lesions[J]. Chin J Magn Reson Imaging, 2022, 13(9): 18-24. DOI: 10.12015/issn.1674-8034.2022.09.004.
[32]
CHEN Z G, LI X, SHA L. Research progress of machine learning for predicting breast cancer response to neoadjuvant chemotherapy based on MRI[J]. Chin J Magn Reson Imaging, 2021, 12(12): 102-104. DOI: 10.12015/issn.1674-8034.2021.12.024.
[33]
ZHAO Q Y, LIN Y. Breast cancer molecular typing prediction based on transfer learning and support vector machine[J]. Chin J Med Phys, 2022, 39(5): 635-639. DOI: 10.3969/j.issn.1005-202X.2022.05.019.
[34]
SUN R, MENG Z J, HOU X W, et al. Prediction of breast cancer molecular subtypes using DCE-MRI based on CNNs combined with ensemble learning[J/OL]. Phys Med Biol, 2021, 66(17) [2022-10-25]. https://iopscience.iop.org/article/10.1088/1361-6560/ac195a. DOI: 10.1088/1361-6560/ac195a.

PREV Application value of arterial spin labeling imaging with dual parameters in evaluating collateral circulation and prognosis of acute ischemic stroke
NEXT Study on the value of mDixon-Quant technique in the diagnosis and prognosis evaluation of invasive ductal breast cancer
  


LINK


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