Development of MRI-based radiomics predictive model for classifying endometrial lesions

Abstract

An unbiased and accurate diagnosis of benign and malignant endometrial lesions is essential for the gynecologist, as each type might require distinct treatment. Radiomics is a quantitative method that could facilitate deep mining of information and quantification of the heterogeneity in images, thereby aiding clinicians in proper lesion diagnosis. The aim of this study is to develop an appropriate predictive model for the classification of benign and malignant endometrial lesions, and evaluate potential clinical applicability of the model. 139 patients with pathologically-confirmed endometrial lesions from January 2018 to July 2020 in two independent centers (center A and B) were finally analyzed. Center A was used for training set, while center B was used for test set. The lesions were manually drawn on the largest slice based on the lesion area by two radiologists. After feature extraction and feature selection, the possible associations between radiomics features and clinical parameters were assessed by Uni- and multi- variable logistic regression. The receiver operator characteristic (ROC) curve and DeLong validation were employed to evaluate the possible predictive performance of the models. Decision curve analysis (DCA) was used to evaluate the net benefit of the radiomics nomogram. A radiomics prediction model was established from the 15 selected features, and were found to be relatively high discriminative on the basis of the area under the ROC curve (AUC) for both the training and the test cohorts (AUC = 0.90 and 0.85, respectively). The radiomics nomogram also showed good performance of discrimination for both the training and test cohorts (AUC = 0.91 and 0.86, respectively), and the DeLong test shows that AUCs were significantly different between clinical parameters and nomogram. The result of DCA demonstrated the clinical usefulness of this novel nomogram method. The predictive model constructed based on MRI radiomics and clinical parameters indicated a highly diagnostic efficiency, thereby implying its potential clinical usefulness for the precise identification and prediction of endometrial lesions.

Figure 1

A diagram depicting overview of the study’s workflow.

Figure 2

The selection of the various features and dimension reduction was performed using LASSO method. (a) Ten-fold cross-validation was used to choose the optimal parameter (λ) with the minimum criteria, thus determining the number of the features. (b) Coefficients for the optimal parameter (λ). A vertical line was drawn at the selected value of log (λ) and showed the coefficients with non-zero. (c) The final selected features and corresponding coefficients.

Figure 3

Radscore comparison of the benign and malignant endometrial lesions on the training and test cohort, respectively (left: training cohort; right: test cohort).

Figure 4

(a) A radiomics nomogram for determining the discrimination between benign and malignant endometrial lesions, which was developed in the training cohort. (b) The calibration curves of the training set (left) and the test set (right).

Figure 5

(a) The ROC curve and corresponding AUC values for the nomogram, radiomics signature and the clinical parameter models for identification of the benign and malignant endometrial lesions (left: training cohort; right: test cohort). (b) The decision curve analysis was used to evaluate the clinical benefit of the models. The green, blue and red lines correspond to the clinical parameter, radiomics signature and radiomics nomogram models respectively. The black line represents an extreme situation where all indicators are positive, while the horizontal red line represents the other extreme situation where all analyzed indicators are negative.