Invasive ductal breast cancer: preoperative predict Ki-67 index based on radiomics of ADC maps
- 41 Downloads
The purpose of this study is to develop a radiomics model for predicting the Ki-67 proliferation index in patients with invasive ductal breast cancer through magnetic resonance imaging (MRI) preoperatively.
Materials and methods
A total of 128 patients who were clinicopathologically diagnosed with invasive ductal breast cancer were recruited. This cohort included 32 negative Ki67 expression (Ki67 proliferation index < 14%) and 96 cases with positive Ki67 expression (Ki67 proliferation index ≥ 14%). All patients had undergone diffusion-weighted imaging (DWI) MRI before surgery on a 3.0T MRI scanner. Radiomics features were extracted from apparent diffusion coefficient (ADC) maps which were obtained by DWI-MRI from patients with invasive ductal breast cancer. 80% of the patients were divided into training set to build radiomics model, and the rest into test set to evaluate its performance. The least absolute shrinkage and selection operator (LASSO) was used to select radiomics features, and then, the logistic regression (LR) model was established using fivefold cross-validation to predict the Ki-67 index. The performance was evaluated by receiver-operating characteristic (ROC) analysis, accuracy, sensitivity and specificity.
Quantitative imaging features (n = 1029) were extracted from ADC maps, and 11 features were selected to construct the LR model. Good identification ability was exhibited by the ADC-based radiomics model, with areas under the ROC (AUC) values of 0.75 ± 0.08, accuracy of 0.71 in training set and 0.72, 0.70 in test set.
The ADC-based radiomics model is a feasible predictor for the Ki-67 index in patients with invasive ductal breast cancer. Therefore, we proposed that three-dimensional imaging features from ADC maps could be used as candidate biomarker for preoperative prediction the Ki-67 index noninvasively.
KeywordsRadiomics Invasive ductal breast cancer Ki-67 MRI
This research was supported in part by grants from the National Natural Science Foundation of China (#81771804).
Compliance with ethical standards
Conflict of interest
The authors have declared that no competing financial interests exist.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Declaration of Helsinki and its later amendments or comparable ethical standards. IRB approval was obtained. This article does not contain any studies with animals performed by any of the authors.
For this type of study, formal consent is not required.
- 2.Goldhirsch A, Wood WC, Coates AS, Gelber RD, Thurlimann B, Senn HJ et al (2011) 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. Ann Oncol 22:1736–1747CrossRefGoogle Scholar
- 15.Liu Y, Kim J, Balagurunathan Y, Li Q, Garcia AL, Stringfield O et al (2016) Radiomic features are associated with EGFR mutation status in lung adenocarcinomas. Clin Lung Cancer 17(441–8):e6Google Scholar
- 19.Freedman D, Pisani R, Purves R (2007) Statistics: fourth international student edition. W.W. Norton & Company. ISBN 9780393930436Google Scholar
- 22.Altay C, Balci P, Altay S, Karasu S, Saydam S, Canda T et al (2014) Diffusion-weighted MR imaging: role in the differential diagnosis of breast lesions. JBR-BTR: organe de la Societe royale belge de radiologie (SRBR) = orgaan van de Koninklijke Belgische Vereniging voor Radiologie (KBVR) 97:211–216Google Scholar
- 24.Li L, Wang K, Sun X, Wang K, Sun Y, Zhang G et al (2015) Parameters of dynamic contrast-enhanced MRI as imaging markers for angiogenesis and proliferation in human breast cancer. Med Sci Monit Int Med J Exp Clin Res 21:376–382Google Scholar
- 28.Gillies RJ (2015) Abstract CN01-01: The radiology reading room of the future. Mol Cancer Ther 14:CN01-CNGoogle Scholar