A Nomogram Based on Molecular Biomarkers and Radiomics to Predict Lymph Node Metastasis in Breast Cancer

Abstract

Background: The aim of this study was to explore the feasibility and efficacy of a non-invasive quantitative imaging evaluation model to assess the lymphatic metastasis of breast cancer based on a radiomics signature constructed using conventional T1-weighted image (T1WI) enhanced MRI and molecular biomarkers.

Methods: Patients with breast cancer diagnosed via lymph biopsies between June 2015 and June 2019 were selected for the study. All patients underwent T1WI contrast-enhancement before treatment; lymph biopsy after surgery; and simultaneous Ki-67, COX-2, PR, Her2 and proliferating cell nuclear antigen detection. All images were imported into ITK-SNAP for whole tumor delineation, and AK software was used for radiomics feature extraction. Next, the radiomics signature Rad-score was constructed after reduction of specific radiomic features. A multiple regression logistic model was built by combining the Rad-score and molecular biomarkers based on the minimum AIC.

Results: In all, 100 patients were enrolled in this study, including 45 with non-lymph node (LN) metastasis and 55 with LN metastasis. A total of 1,051 texture feature parameters were extracted, and LASSO was used to reduce the dimensionality of the radiomics features. The log(λ) was set to 0.002786, and 19 parameters were retained for the construction of the radiomics tag Rad-score. ROC was used to evaluate the diagnostic efficiency of Rad-score: the area under the ROC curve (AUC) of the Rad-score for identifying non-lymphatic and lymphatic metastases was 0.891 in the training cohort and 0.744 in the validation cohort. With the incorporation of tumor molecular markers, the AUCs of the training cohort and validation cohort of the nomogram were 0.936 and 0.793, respectively, which were notably higher than the AUCs of the clinical parameters in the training and validation cohorts (0.719 and 0.588, respectively).

Conclusion: The combined model constructed using the Rad-score and molecular biomarkers can be used as an effective non-invasive method to assess LN metastasis of breast cancer. Furthermore, it can be used to quantitatively evaluate the risk of breast cancer LN metastasis before surgery.

Keywords: breast cancer; diagnostics; lymph node metastasis; molecular biomarkers; radiomics.

Figure 1

Flowchart depicting model design.

Figure 2

Feature selection and Rad-score building by LASSO. (A) 10-fold cross validation was used to predict binomial deviance of the Rad-score building by different lambda values. (B) The coefficient profiles of the radiomics features by different lambda values.

Figure 3

The coefficients of radiomic features to construct the Rad-score.

Figure 4

The difference and ROC curves of the Rad-score in the training and validation cohorts. (A, B) Mann-Whitney U validation was used to analyze the difference between lymph node (LN)-positive and -negative patients in the training and validation cohorts. (C, D) ROC curve of the Rad-score in the training and validation cohort. AUC was used to predict the diagnostic performance between the LN-positive and -negative patients.

Figure 5

Nomogram combining the clinical data and Rad-score. (A) The multiple logistic regression model constructed using the Rad-score and clinical data visualized by the nomogram. (B, C) The ROC curves of the Rad-score, clinical data, and nomogram in the training and validation cohorts.

Figure 6

The diagnostic performance of nomogram evaluation. (A) Decision curve analysis of the Rad-score, clinical data, and nomogram. The y-axis indicates the clinical benefits while the x-axis indicates the clinical risk to predict lymph node (LN) metastasis. The “All line” indicates a randomized evaluation of the LN metastasis. The pink line indicates no method was used to evaluate the LN metastasis. (A–C) Calibration curves of the nomogram in the training and validation cohorts.