A Nomogram Based on Radiomics with Mammography Texture Analysis for the Prognostic Prediction in Patients with Triple-Negative Breast Cancer

Abstract

Objectives: To develop and validate a radiomics-based nomogram with texture features from mammography for the prognostic prediction in patients with early-stage triple-negative breast cancer (TNBC).

Methods: The study included 200 consecutive patients with TNBC (training cohort: n = 133, validation cohort: n = 67). A total of 136 mammography-derived textural features were extracted, and LASSO (least absolute shrinkage and selection operator) was applied to select features for building the radiomics score (Rad-score). After univariate and multivariate logistic regression, a radiomics-based nomogram was constructed with independent prognostic factors. The discrimination and calibration power were assessed, and further the clinical applicability of the nomograms was evaluated.

Results: Among the 136 mammography-derived textural features, fourteen were used to build the Rad-score after LASSO regression. A radiomics nomogram that incorporates Rad-score and pN stage was constructed. This nomogram achieved a C-index of 0.873 (95% CI: 0.758-0.989) for predicting iDFS (invasive disease-free survival), which outperformed the clinical model. Moreover, it is feasible to stratify patients into high-risk and low-risk groups based on the optimal cut-off point of Rad-score. The validations of the nomogram confirmed favorable discrimination and considerable predictive efficiency.

Conclusions: The radiomics nomogram that incorporates Rad-score and pN stage exhibited favorable performance in the prediction of iDFS in patients with early-stage TNBCs.

Figure 1

Workflow of radiomic signature building. Abbreviation: ROI = region of interest; LIFEx = Local Image Feature Extraction; LASSO = the least absolute shrinkage and selection operator.

Figure 2

LASSO selection and the predictive efficacy of radiomics features. (a). Tuning parameter (λ) selection with minimum criteria-based 10-fold cross-validation in the LASSO model. Binomial deviances (y-axis) were plotted as a function of log (λ) (lower x-axis), and the upper x-axis represents the average number of predictors. The dotted vertical lines were drawn at the optimal values of λ and the value that gave the minimum average binomial deviance was used to select radiomics features. The optimal λ value of 0.01 (log (λ) = −4.610) was selected. (b) LASSO coefficient profiles of the 136 texture features. Each colored curve represents the trajectory of the change of an independent variable. At the value selected using 10-fold cross-validation, the optimal λ resulted in fourteen coefficients.

Figure 3

Radiomics nomogram to estimate iDFS for patients with triple-negative breast cancers and its discrimination performance. (a) The radiomics nomogram was developed by incorporating pN stage and radiomics score. b−e. Calibration curves of the nomogram for the estimation of 1-year (b), 2-year (c), 5-year (d), and 8-year (e) iDFS in the training cohort. The diagonal line represents a perfect match between the predicted (x-axis) and actual (y-axis) probabilities, and the colored line represents the predictive performance of the nomogram. The closeness between the two lines indicates the predictive accuracy of the nomogram.

Figure 4

Kaplan–Meier survival analyses of high-risk and low-risk patients in the training (a) and validation cohort (b).

Figure 5

Decision curve analysis for each model in survival prediction in patients with triple-negative breast cancers (TNBCs). The x-axis represents the threshold probability and the y-axis represents the net benefit. The grey line represents the assumption that all patients had experienced events of invasive disease. The black horizontal line represents the assumption that no patient had invasive disease. The decision curves show that using the radiomics nomograms to predict survival adds more benefit for TNBC patients than all other models. ^∗Radiomics score binarily classified as high- and low-risk groups.