Pharmacokinetic parameters and radiomics model based on dynamic contrast enhanced MRI for the preoperative prediction of sentinel lymph node metastasis in breast cancer

Abstract

Background To establish pharmacokinetic parameters and a radiomics model based on dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) for predicting sentinel lymph node (SLN) metastasis in patients with breast cancer. Methods A total of 164 breast cancer patients confirmed by pathology were prospectively enrolled from December 2017 to May 2018, and underwent DCE-MRI before surgery. Pharmacokinetic parameters and radiomics features were derived from DCE-MRI data. Least absolute shrinkage and selection operator (LASSO) regression method was used to select features, which were then utilized to construct three classification models, namely, the pharmacokinetic parameters model, the radiomics model, and the combined model. These models were built through the logistic regression method by using 10-fold cross validation strategy and were evaluated on the basis of the receiver operating characteristics (ROC) curve. An independent validation dataset was used to confirm the discriminatory power of the models. Results Seven radiomics features were selected by LASSO logistic regression. The radiomics model, the pharmacokinetic parameters model, and the combined model yielded area under the curve (AUC) values of 0.81 (95% confidence interval [CI]: 0.72 to 0.89), 0.77 (95% CI: 0.68 to 0.86), and 0.80 (95% CI: 0.72 to 0.89), respectively, for the training cohort and 0.74 (95% CI: 0.59 to 0.89), 0.74 (95% CI: 0.59 to 0.90), and 0.76 (95% CI: 0.61 to 0.91), respectively, for the validation cohort. The combined model showed the best performance for the preoperative evaluation of SLN metastasis in breast cancer. Conclusions The model incorporating radiomics features and pharmacokinetic parameters can be conveniently used for the individualized preoperative prediction of SLN metastasis in patients with breast cancer.

Development and Internal Validation of a Preoperative Prediction Model for Sentinel Lymph Node Status in Breast Cancer: Combining Radiomics Signature and Clinical Factors

“…Nevertheless, in our study, for intratumoral radiomic feature from post-contrast phase, first-order features (Variance, Quantile5, MeanDeviation) were mainly selected to predict negative SLN, which also implied the tumor heterogeneity. Moreover, the selected features from whole tumor in our study also included pharmacokinetic parameters (BF_10percent, TTP_25percent, TTP_Max, MTT_Max, MAXSlope_Area) after histogram analysis, which is consistent with a previous study (31), suggesting that massive angiogenesis in tumor may contribute to the perfusion change.…”

“…As an emerging tool for medical application in recent years, radiomics provides a large number of quantitative features derived from post-contrast images based on DCE-MRI. Liu et al combined pharmacokinetic parameters and radiomic features of maximum layer in primary tumor to predict SLN status and obtained a satisfactory performance (AUC 0.80) (31). Pharmacokinetic parameters can also be further analyzed by histogram, one kind of radiomics analysis, which has the potential to be a noninvasive biomarker for preoperative differentiation of molecular subtypes (32), lymph node metastasis (33), and proliferative activities (34) of breast cancer.…”

Sentinel Lymph Node Metastasis on Clinically Negative Patients: Preliminary Results of a Machine Learning Model Based on Histopathological Features

“…What emerges, and which is important to underline to a public of biomedical data scientists or clinician with a transactional interest field, is that the maximum informative power contained in the only characteristics considered for the prediction of the sentinel lymph node status does not exceed 62-63% on the independent test. For this reason, encouraged by recent studies with improved results in the prediction of the lymph node metastasis probability thanks to the joint use of histopathologic and radiomic features [6,[40][41][42][43][44][45][46][47][48][49][50][51][52][53][54], in our future works we will also involve radiomic features extracted from first-level radiological examinations, such as ultrasound and mammography.…”

DataSheet_1.docx

“…We found that the AUC was improved from 0.799 to 0.839 for the radiomics model combining tumor with FGT after further involving the clinical factor of PR, which was consistent with a previous study (16). However, different studies obtained different AUCs of predictive models based on radiomic features from intratumoral and peritumoral regions and clinical factors (16,17,31,35). One of the possible reasons is that we predict negative SLN instead of positive SLN.…”