Abstract
PURPOSE: The aim of this study was to explore the application value of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics and heterogeneity analysis in the differentiation of molecular subtypes of luminal and non-luminal breast cancer. METHODS: In this retrospective study, 388 female breast cancer patients (48.37 ± 9.41 years) with luminal (n = 190) and non-luminal (n = 198) molecular subtypes who received surgical treatment at Jilin Cancer Hospital were recruited from January 2019 to June 2023. All patients underwent breast MRI scan and DCE scan before surgery. The patients were then divided into a training set (n = 272) and a validation set (n = 116) in a 7:3 ratio. The three-dimensional texture feature parameters of the breast lesion areas were extracted. Four tumor heterogeneity parameters, including type I curve proportion, type II curve proportion, type III curve proportion and tumor heterogeneity values were calculated and normalized. Five machine learning (ML) models, including the logistic regression, naive Bayes algorithm (NB), k-nearest neighbor (KNN), decision tree algorithm (DT) and extreme gradient boosting (XGBoost) model were used to process the training data and were further validated. The best ML model was selected according to the performance in the validation set. RESULTS: In luminal subtype breast lesions, type III curve proportion and heterogeneity index were significantly lower than the corresponding parameters of the non-luminal subtype lesions both in the training set and validation set. Eight features together with four heterogeneity-related parameters with significant differences between luminal and non-luminal groups were retained as radiomics signatures for constructing the prediction model. The logistic regression ML model achieved the best performance in the validation set with the highest area under the curve value (0.93), highest accuracy (86.94%), sensitivity (87.55%) and specificity (86.25%). CONCLUSION: The radiomics and heterogeneity analysis based on the DCE-MRI exhibit good application value in discriminating luminal and non-luminal subtype breast cancer. The logistic regression model demonstrates the best predictive performance among various machine learning models.