Preoperative prediction of lymph node metastasis in endometrial cancer patients via an intratumoral and peritumoral multiparameter MRI radiomics nomogram

Abstract

Introduction: While lymph node metastasis (LNM) plays a critical role in determining treatment options for endometrial cancer (EC) patients, the existing preoperative methods for evaluating the lymph node state are not always satisfactory. This study aimed to develop and validate a nomogram based on intra- and peritumoral radiomics features and multiparameter magnetic resonance imaging (MRI) features to preoperatively predict LNM in EC patients.

Methods: Three hundred and seventy-four women with histologically confirmed EC were divided into training (n = 220), test (n = 94), and independent validation (n = 60) cohorts. Radiomic features were extracted from intra- and peritumoral regions via axial T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) mapping. A radiomics model (annotated as the Radscore) was established using the selected features from different regions. The clinical parameters were statistically analyzed. A nomogram was developed by combining the Radscore and the most predictive clinical parameters. Decision curve analysis (DCA) and the net reclassification index (NRI) were used to assess the clinical benefit of using the nomogram.

Results: Nine radiomics features were ultimately selected from the intra- and peritumoral regions via ADC mapping and T2WI. The nomogram combining the Radscore, serum CA125 level, and tumor area ratio achieved the highest AUCs in the training, test and independent validation sets (nomogram vs. Radscore vs. clinical model: 0.878 vs. 0.850 vs. 0.674 (training), 0.877 vs. 0.838 vs. 0.668 (test), and 0.864 vs. 0.836 vs. 0.618 (independent validation)). The DCA and NRI results revealed the nomogram had greater diagnostic performance and net clinical benefits than the Radscore alone.

Conclusion: The combined intra- and peritumoral region multiparameter MRI radiomics nomogram showed good diagnostic performance and could be used to preoperatively predict LNM in patients with EC.

Keywords: endometrial cancer; lymph node; lymphatic metastasis; magnetic resonance imaging; radiomics.

Figure 1

Flow chart demonstrating how the study population was chosen and the exclusion criteria applied.

Figure 2

The radiomic workflow included manual segmentation of 3D VOIs from intra- and peritumoral regions, extraction of radiomic features, feature selection through LASSO regression, model development using nomograms, and evaluation of diagnostic performance via receiver operating characteristic (ROC) curve analysis.

Figure 3

Methods for measuring tumor morphology parameters. (A) Measurements of the tumor’s maximum transverse diameter (solid line, x) and anteroposterior diameter (dotted line, y) were taken on oblique axial T2W images. (B) On sagittal T2W images, the tumor’s maximum craniocaudal diameter (solid line, z) and maximum anteroposterior diameter were measured (dotted line, APsag). (C) The tumor border on the DW image (reverse image) is shown by the white solid line. (D) The uterine border on the axial T2W image is depicted by the white solid line.

Figure 4

SMOTE workflow. AUC, area under the curve; ACC, accuracy; SPE, specificity; SEN, sensitivity; NRI, net reclassification improvement; LNM, lymph node metastasis; SMOTE. synthetic minority oversampling technique.

Figure 5

Explanation of the radiomics nomogram. (A) The nomogram of patients in the training cohort, which was developed by incorporating clinical (serum CA125 level) and morphological (TAR) features and the radiomics score (Radscore). According to this nomogram, the greater the risk is, the greater the likelihood that the patient will have LNM. (B) Comparison of ROC curves for different prediction models (n = 3) in differentiating LNM-positive and LNM-negative EC patients in the training cohort. The radiomics nomogram showed the highest AUC of 0.878 (95% CI, 0.823-0.907). In the test (C, AUC of 0.877, 95% CI: 0.831-0.914) and external validation (D, AUC of 0.864, 95% CI, 0.815-0.901) cohorts, the radiomics nomogram achieved the highest AUC.

Figure 6

Graphs showing the calibration curves and decision curve analysis (DCA) results of the nomogram. (A–C) The calibration curves of the nomogram in the training (A), test (B), and external validation cohorts (C); (D–F) for DCAs; the net benefit is on the vertical axis; the threshold probability is on the horizontal axis; the gray line represents the assumption that all patients are classified as having LNM; the black line represents the assumption that none of the patients are classified as having LNM; the green line represents the clinical model; the red line represents the radiomics score; the blue line represents the nomogram; and the DCA of the nomogram in the training (D), test (E), and external validation cohorts (F). LNM, lymph node metastasis.