DBT-based radiomics for differentiating benign and malignant breast lesions
JIANG Wen-yan1, NIU Shu-xian2, ZHANG Meng-yao2, CUI Lin-peng2, #br#
DONG Yue1, AI Hua1, ZHOU Xiao-ya3, YU Tao1, LUO Ya-hong1
Author information+
1. Department of Imaging, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, Shenyang 110042, China;
2. Department of Biomedical Engineering, China Medical University, Shenyang 110122, China;
3. College of Basic Medicine, Jining Medical University, Jining Shandong 272067, China
Objective: To evaluate the role of DBT-based radiomics in differentiating benign and malignant breast lesions. Methods: Breast DBT data of 160 patients were collected from Liaoning Cancer Hospital from September 2017 to April 2018 were analyzed. Radiomics features were extracted and analyzed. A nomogram model for distinguishing benign and malignant lesions was constructed. The clinical applicability of the nomogram was further evaluated by decision curve analysis. The predictive abilities of the models were evaluated by ROC curves and AUC values. Result: The AUC values of the constructed nomogram were 0.942(SEN=0.833, SPE=0.928) and 0.928(SEN=0.926, SPE=0.839) in the training and validation cohorts, respectively. The DCA analyses showed that our nomogram had good clinical value. Conclusion: Our nomogram model based on breast DBT image features has great potential in non-invasive distinguishing benign and malignant lesions.
JIANG Wen-yan1, NIU Shu-xian2, ZHANG Meng-yao2, CUI Lin-peng2,.
DBT-based radiomics for differentiating benign and malignant breast lesions[J]. Journal of China Clinic Medical Imaging. 2020, 31(6): 398-402 https://doi.org/10.12117/jccmi.2020.06.005
中图分类号：
Ｒ737.9
Ｒ655.8
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1]McGuire A, Brown JA, Malone C, et al. Effects of age on the detection and management of breast cancer[J]. Cancers, 2015, 7(2): 908-929.
[2]WY Xie, YS Li, YD Ma. Breast mass classification in digital mammography based on extreme learning machine[J]. Neurocomputing, 2016, 173(3): 930-941.
[3]Michell MJ. Breast screening review—a radiologist’s perspective[J]. Br J Radiol, 2012, 85(1015): 845-1026.
[4]Vedantham S, Karellas A, Vijayaraghavan GR, et al. Digital Breast Tomosynthesis: State of the Art[J]. Radiology, 2015, 277(3): 663-684.
[5]Miglioretti DL, Abraham L, Lee CI, et al. Digital Breast Tomosynthesis: Radiologist Learning Curve[J]. Radiology, 2019, 26(2): 182305.
[6]Tagliafico AS, Valdora F, Mariscotti G, et al. An exploratory radiomics analysis on digital breast tomosynthesis in women with mammographically negative dense breasts[J]. Breast, 2018, 40: 92-96.
[7]Hatt M, Tixier F, Visvikis D, et al. Radiomics in PET?蛐CT: More than meets the eye?[J]. J Nucl Med, 2017, 58(3): 365-366.
[8]Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data[J]. Radiology, 2016, 278(2): 563-577.
[9]Aerts HJ, Velazquez ER, Leijenaar RT, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach[J]. Nat Commun, 2014, 5(1): 4006.
[10]Ma W, Zhao Y, Ji Y, et al. Breast cancer molecular subtype prediction by mammographic radiomic features[J]. Acad Radiol, 2019, 26(2): 196-201.
[11]Lee SE, Han K, Kwak JY, et al. Radiomics of US texture features in differential diagnosis between triple-negative breast cancer and fibroadenoma[J]. Sci Rep, 2018, 8(1): 13546.
[12]Xiong Q, Zhou X, Liu Z, et al. Multiparametric MRI-based radiomics analysis for prediction of breast cancers insensitive to neoadjuvant chemotherapy[J]. Clin Transl Oncol, 2019, 22(1): 50-59.
[13]Bevilacqua V, Brunetti A, Guerriero A, et al. A performance comparison between shallow and deeper neural networks supervised classification of tomosynthesis breast lesions images[J]. Congn Syst Res, 2019, 53: 3-19.
[14]Zhou H, Dong D, Chen B, et al. Diagnosis of distant metastasis of lung cancer: based on clinical and radiomic features[J]. Transl Oncol, 2018, 11(1): 31-36.
[15]Wang H, Zhou Z, Li Y, et al. Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images[J]. EJNMMI Res, 2017, 7(1): 11.
[16]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.
[17]Yang X, Pan X, Liu H, et al. A new approach to predict lymph node metastasis in solid lung adenocarcinoma: a radiomics nomogram[J]. J Thorac Dis, 2018, 10(7): S807-S819.
[18]Helvie MA. Digital Mammography Imaging: Breast Tomosynthesis and Advanced Applications[J]. Radiol Clin North Am, 2010, 48(5): 917-929.
[19]Valdora F, Houssami N, Rossi F, et al. Rapid review: radiomics and breast cancer[J]. Breast Cancer Res Treat, 2018, 169(2): 217-229.
[20]Ma W, Zhao Y, Ji Y, et al. Breast cancer molecular subtype prediction by mammographic radiomic features[J]. Acad Radiol, 2019, 26(2): 196-201.
